id
stringlengths 6
30
| multi_turn
bool 2
classes | functions
stringlengths 2
28.2k
| tools
stringlengths 2
31.8k
| missed_functions
stringclasses 115
values | initial_config
stringclasses 195
values | involved_classes
listlengths 0
2
| turns
stringlengths 2.76k
34.1k
| language
stringclasses 3
values | test_category
stringclasses 17
values | subset
stringclasses 17
values | ground_truth
stringlengths 2
7.23k
|
|---|---|---|---|---|---|---|---|---|---|---|---|
simple_209
| false |
[{"name": "public_library.find_nearby", "description": "Locate nearby public libraries based on specific criteria like English fiction availability and Wi-Fi.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city and state, e.g. Boston, MA"}, "facilities": {"type": "array", "items": {"type": "string", "enum": ["Wi-Fi", "Reading Room", "Fiction", "Children Section", "Cafe"]}, "description": "Facilities and sections in public library."}}, "required": ["location", "facilities"]}}]
|
[{"type": "function", "function": {"name": "public_library_find_nearby", "description": "Locate nearby public libraries based on specific criteria like English fiction availability and Wi-Fi. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. Boston, MA"}, "facilities": {"type": "array", "items": {"type": "string", "enum": ["Wi-Fi", "Reading Room", "Fiction", "Children Section", "Cafe"]}, "description": "Facilities and sections in public library."}}, "required": ["location", "facilities"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'public_library.find_nearby', 'description': 'Locate nearby public libraries based on specific criteria like English fiction availability and Wi-Fi. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city and state, e.g. Boston, MA'}, 'facilities': {'type': 'array', 'items': {'type': 'string', 'enum': ['Wi-Fi', 'Reading Room', 'Fiction', 'Children Section', 'Cafe']}, 'description': 'Facilities and sections in public library.'}}, 'required': ['location', 'facilities']}}]\n"}, {"role": "user", "content": "Locate the nearest public library in Boston, Massachusetts with English fiction section and free Wi-Fi."}]]
|
Python
|
simple
|
simple
|
[{"public_library.find_nearby": {"location": ["Boston, MA", "Boston, Massachusetts"], "facilities": [["Fiction", "Wi-Fi"], ["Wi-Fi", "Fiction"]]}}]
|
simple_210
| false |
[{"name": "get_news", "description": "Fetches the latest news on a specific topic.", "parameters": {"type": "dict", "properties": {"topic": {"type": "string", "description": "The subject for the news topic."}, "quantity": {"type": "integer", "description": "Number of articles to fetch."}, "region": {"type": "string", "description": "The geographical region for the news. Default is 'US'."}}, "required": ["topic", "quantity"]}}]
|
[{"type": "function", "function": {"name": "get_news", "description": "Fetches the latest news on a specific topic. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"topic": {"type": "string", "description": "The subject for the news topic."}, "quantity": {"type": "integer", "description": "Number of articles to fetch."}, "region": {"type": "string", "description": "The geographical region for the news. Default is 'US'."}}, "required": ["topic", "quantity"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_news', 'description': 'Fetches the latest news on a specific topic. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'topic': {'type': 'string', 'description': 'The subject for the news topic.'}, 'quantity': {'type': 'integer', 'description': 'Number of articles to fetch.'}, 'region': {'type': 'string', 'description': \"The geographical region for the news. Default is 'US'.\"}}, 'required': ['topic', 'quantity']}}]\n"}, {"role": "user", "content": "Get 5 latest news on Bitcoin in US"}]]
|
Python
|
simple
|
simple
|
[{"get_news": {"topic": ["Bitcoin"], "quantity": [5], "region": ["US", ""]}}]
|
simple_211
| false |
[{"name": "send_email", "description": "Send an email to the specified email address.", "parameters": {"type": "dict", "properties": {"to": {"type": "string", "description": "The email address to send to."}, "subject": {"type": "string", "description": "The subject of the email."}, "body": {"type": "string", "description": "The body content of the email."}, "cc": {"type": "string", "description": "The email address to carbon copy. Default is empty if not specified."}, "bcc": {"type": "string", "description": "The email address to blind carbon copy. Default is empty if not specified."}}, "required": ["to", "subject", "body"]}}]
|
[{"type": "function", "function": {"name": "send_email", "description": "Send an email to the specified email address. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"to": {"type": "string", "description": "The email address to send to."}, "subject": {"type": "string", "description": "The subject of the email."}, "body": {"type": "string", "description": "The body content of the email."}, "cc": {"type": "string", "description": "The email address to carbon copy. Default is empty if not specified."}, "bcc": {"type": "string", "description": "The email address to blind carbon copy. Default is empty if not specified."}}, "required": ["to", "subject", "body"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'send_email', 'description': 'Send an email to the specified email address. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'to': {'type': 'string', 'description': 'The email address to send to.'}, 'subject': {'type': 'string', 'description': 'The subject of the email.'}, 'body': {'type': 'string', 'description': 'The body content of the email.'}, 'cc': {'type': 'string', 'description': 'The email address to carbon copy. Default is empty if not specified.'}, 'bcc': {'type': 'string', 'description': 'The email address to blind carbon copy. Default is empty if not specified.'}}, 'required': ['to', 'subject', 'body']}}]\n"}, {"role": "user", "content": "Send an email to John Doe at john.doe@example.com with the subject 'Meeting' and body 'Let's meet at 10 AM tomorrow'."}]]
|
Python
|
simple
|
simple
|
[{"send_email": {"to": ["john.doe@example.com"], "subject": ["Meeting"], "body": ["Let's meet at 10 AM tomorrow", "Let's meet at 10 AM tomorrow."], "cc": [""], "bcc": [""]}}]
|
simple_212
| false |
[{"name": "get_stock_info", "description": "Retrieves information about a specific stock based on company's name.", "parameters": {"type": "dict", "properties": {"company_name": {"type": "string", "description": "The name of the company."}, "detail_level": {"type": "string", "description": "Level of detail for stock information. Can be 'summary' or 'detailed'."}, "market": {"type": "string", "description": "The stock market of interest. Default is 'NASDAQ'"}}, "required": ["company_name", "detail_level"]}}]
|
[{"type": "function", "function": {"name": "get_stock_info", "description": "Retrieves information about a specific stock based on company's name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"company_name": {"type": "string", "description": "The name of the company."}, "detail_level": {"type": "string", "description": "Level of detail for stock information. Can be 'summary' or 'detailed'."}, "market": {"type": "string", "description": "The stock market of interest. Default is 'NASDAQ'"}}, "required": ["company_name", "detail_level"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_stock_info', 'description': \"Retrieves information about a specific stock based on company's name. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'company_name': {'type': 'string', 'description': 'The name of the company.'}, 'detail_level': {'type': 'string', 'description': \"Level of detail for stock information. Can be 'summary' or 'detailed'.\"}, 'market': {'type': 'string', 'description': \"The stock market of interest. Default is 'NASDAQ'\"}}, 'required': ['company_name', 'detail_level']}}]\n"}, {"role": "user", "content": "Give me detail information about stocks of Apple Inc."}]]
|
Python
|
simple
|
simple
|
[{"get_stock_info": {"company_name": ["Apple Inc."], "detail_level": ["detailed"], "market": ["", "NASDAQ"]}}]
|
simple_213
| false |
[{"name": "flight.book", "description": "Book a direct flight for a specific date and time from departure location to destination location.", "parameters": {"type": "dict", "properties": {"departure_location": {"type": "string", "description": "The location you are departing from."}, "destination_location": {"type": "string", "description": "The location you are flying to."}, "date": {"type": "string", "description": "The date of the flight. Accepts standard date format e.g., 2022-04-28."}, "time": {"type": "string", "description": "Preferred time of flight. Default is 'morning'."}, "direct_flight": {"type": "boolean", "description": "If set to true, only direct flights will be searched. Default is false."}}, "required": ["departure_location", "destination_location", "date"]}}]
|
[{"type": "function", "function": {"name": "flight_book", "description": "Book a direct flight for a specific date and time from departure location to destination location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"departure_location": {"type": "string", "description": "The location you are departing from."}, "destination_location": {"type": "string", "description": "The location you are flying to."}, "date": {"type": "string", "description": "The date of the flight. Accepts standard date format e.g., 2022-04-28."}, "time": {"type": "string", "description": "Preferred time of flight. Default is 'morning'."}, "direct_flight": {"type": "boolean", "description": "If set to true, only direct flights will be searched. Default is false."}}, "required": ["departure_location", "destination_location", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'flight.book', 'description': 'Book a direct flight for a specific date and time from departure location to destination location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'departure_location': {'type': 'string', 'description': 'The location you are departing from.'}, 'destination_location': {'type': 'string', 'description': 'The location you are flying to.'}, 'date': {'type': 'string', 'description': 'The date of the flight. Accepts standard date format e.g., 2022-04-28.'}, 'time': {'type': 'string', 'description': \"Preferred time of flight. Default is 'morning'.\"}, 'direct_flight': {'type': 'boolean', 'description': 'If set to true, only direct flights will be searched. Default is false.'}}, 'required': ['departure_location', 'destination_location', 'date']}}]\n"}, {"role": "user", "content": "Book a direct flight from San Francisco to London for 2022-04-27 afternoon"}]]
|
Python
|
simple
|
simple
|
[{"flight.book": {"departure_location": ["San Francisco", "SF"], "destination_location": ["London"], "date": ["2022-04-27", "04/27/2022", "Apr 27, 2022"], "time": ["afternoon", ""], "direct_flight": [true]}}]
|
simple_214
| false |
[{"name": "event_finder.find_upcoming", "description": "Find upcoming events of a specific genre in a given location.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city and state where the search will take place, e.g. New York, NY."}, "genre": {"type": "string", "description": "The genre of events."}, "days_ahead": {"type": "integer", "description": "The number of days from now to include in the search.", "default": 7}}, "required": ["location", "genre"]}}]
|
[{"type": "function", "function": {"name": "event_finder_find_upcoming", "description": "Find upcoming events of a specific genre in a given location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state where the search will take place, e.g. New York, NY."}, "genre": {"type": "string", "description": "The genre of events."}, "days_ahead": {"type": "integer", "description": "The number of days from now to include in the search.", "default": 7}}, "required": ["location", "genre"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'event_finder.find_upcoming', 'description': 'Find upcoming events of a specific genre in a given location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city and state where the search will take place, e.g. New York, NY.'}, 'genre': {'type': 'string', 'description': 'The genre of events.'}, 'days_ahead': {'type': 'integer', 'description': 'The number of days from now to include in the search.', 'default': 7}}, 'required': ['location', 'genre']}}]\n"}, {"role": "user", "content": "Search for upcoming month rock concerts in New York."}]]
|
Python
|
simple
|
simple
|
[{"event_finder.find_upcoming": {"location": ["New York", "New York, NY", "NYC"], "genre": ["Rock", "rock"], "days_ahead": [30]}}]
|
simple_215
| false |
[{"name": "movie_details.brief", "description": "This function retrieves a brief about a specified movie.", "parameters": {"type": "dict", "properties": {"title": {"type": "string", "description": "Title of the movie"}, "extra_info": {"type": "boolean", "description": "Option to get additional information like Director, Cast, Awards etc.", "default": "false"}}, "required": ["title"]}}]
|
[{"type": "function", "function": {"name": "movie_details_brief", "description": "This function retrieves a brief about a specified movie. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"title": {"type": "string", "description": "Title of the movie"}, "extra_info": {"type": "boolean", "description": "Option to get additional information like Director, Cast, Awards etc.", "default": "false"}}, "required": ["title"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'movie_details.brief', 'description': 'This function retrieves a brief about a specified movie. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'title': {'type': 'string', 'description': 'Title of the movie'}, 'extra_info': {'type': 'boolean', 'description': 'Option to get additional information like Director, Cast, Awards etc.', 'default': 'false'}}, 'required': ['title']}}]\n"}, {"role": "user", "content": "Give me a brief on movie 'Interstellar'"}]]
|
Python
|
simple
|
simple
|
[{"movie_details.brief": {"title": ["Interstellar"], "extra_info": ["", false]}}]
|
simple_216
| false |
[{"name": "sentiment_analysis", "description": "Perform sentiment analysis on a given piece of text.", "parameters": {"type": "dict", "properties": {"text": {"type": "string", "description": "The text on which to perform sentiment analysis."}, "language": {"type": "string", "description": "The language in which the text is written."}}, "required": ["text", "language"]}}]
|
[{"type": "function", "function": {"name": "sentiment_analysis", "description": "Perform sentiment analysis on a given piece of text. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"text": {"type": "string", "description": "The text on which to perform sentiment analysis."}, "language": {"type": "string", "description": "The language in which the text is written."}}, "required": ["text", "language"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sentiment_analysis', 'description': 'Perform sentiment analysis on a given piece of text. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'text': {'type': 'string', 'description': 'The text on which to perform sentiment analysis.'}, 'language': {'type': 'string', 'description': 'The language in which the text is written.'}}, 'required': ['text', 'language']}}]\n"}, {"role": "user", "content": "Analyze the sentiment of a customer review 'I love the food here! It's always fresh and delicious.'."}]]
|
Python
|
simple
|
simple
|
[{"sentiment_analysis": {"text": ["I love the food here! It's always fresh and delicious."], "language": ["english", "English", "en"]}}]
|
simple_217
| false |
[{"name": "fMRI.analyze", "description": "This function takes in fMRI data to output analyzed data.", "parameters": {"type": "dict", "properties": {"data_source": {"type": "string", "description": "The path where the data is stored."}, "sequence_type": {"type": "string", "description": "Type of fMRI sequence"}, "smooth": {"type": "integer", "description": "Spatial smoothing FWHM. In mm."}, "voxel_size": {"type": "integer", "description": "Size of isotropic voxels in mm.", "default": 3}}, "required": ["data_source", "sequence_type", "smooth"]}}]
|
[{"type": "function", "function": {"name": "fMRI_analyze", "description": "This function takes in fMRI data to output analyzed data. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"data_source": {"type": "string", "description": "The path where the data is stored."}, "sequence_type": {"type": "string", "description": "Type of fMRI sequence"}, "smooth": {"type": "integer", "description": "Spatial smoothing FWHM. In mm."}, "voxel_size": {"type": "integer", "description": "Size of isotropic voxels in mm.", "default": 3}}, "required": ["data_source", "sequence_type", "smooth"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'fMRI.analyze', 'description': 'This function takes in fMRI data to output analyzed data. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'data_source': {'type': 'string', 'description': 'The path where the data is stored.'}, 'sequence_type': {'type': 'string', 'description': 'Type of fMRI sequence'}, 'smooth': {'type': 'integer', 'description': 'Spatial smoothing FWHM. In mm.'}, 'voxel_size': {'type': 'integer', 'description': 'Size of isotropic voxels in mm.', 'default': 3}}, 'required': ['data_source', 'sequence_type', 'smooth']}}]\n"}, {"role": "user", "content": "Analyze my fMRI data in ~/data/myfMRI.nii from a multi-band sequence, that is smoothed at 6mm with an isotropic voxel size of 2mm."}]]
|
Python
|
simple
|
simple
|
[{"fMRI.analyze": {"data_source": ["~/data/myfMRI.nii"], "sequence_type": ["multi-band"], "smooth": [6], "voxel_size": [2]}}]
|
simple_218
| false |
[{"name": "patient.get_mri_report", "description": "Fetch the brain MRI report of the patient for a given status.", "parameters": {"type": "dict", "properties": {"patient_id": {"type": "string", "description": "The patient identifier."}, "mri_type": {"type": "string", "description": "Type of the MRI. Default to be 'brain'.", "enum": ["brain", "spinal", "chest", "abdominal"]}, "status": {"type": "string", "description": "Status of the report, could be 'in progress', 'concluded' or 'draft'.", "enum": ["in progress", "concluded", "draft"]}}, "required": ["patient_id", "status"]}}]
|
[{"type": "function", "function": {"name": "patient_get_mri_report", "description": "Fetch the brain MRI report of the patient for a given status. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"patient_id": {"type": "string", "description": "The patient identifier."}, "mri_type": {"type": "string", "description": "Type of the MRI. Default to be 'brain'.", "enum": ["brain", "spinal", "chest", "abdominal"]}, "status": {"type": "string", "description": "Status of the report, could be 'in progress', 'concluded' or 'draft'.", "enum": ["in progress", "concluded", "draft"]}}, "required": ["patient_id", "status"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'patient.get_mri_report', 'description': 'Fetch the brain MRI report of the patient for a given status. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'patient_id': {'type': 'string', 'description': 'The patient identifier.'}, 'mri_type': {'type': 'string', 'description': \"Type of the MRI. Default to be 'brain'.\", 'enum': ['brain', 'spinal', 'chest', 'abdominal']}, 'status': {'type': 'string', 'description': \"Status of the report, could be 'in progress', 'concluded' or 'draft'.\", 'enum': ['in progress', 'concluded', 'draft']}}, 'required': ['patient_id', 'status']}}]\n"}, {"role": "user", "content": "Given patient with id 546382, retrieve their brain MRI report with the status 'concluded'."}]]
|
Python
|
simple
|
simple
|
[{"patient.get_mri_report": {"patient_id": ["546382"], "mri_type": ["brain", ""], "status": ["concluded"]}}]
|
simple_219
| false |
[{"name": "get_neuron_coordinates", "description": "Retrieve the coordinates of the specified neuron in the rat's brain.", "parameters": {"type": "dict", "properties": {"neuron_type": {"type": "string", "description": "Type of neuron to find. For instance, GABA, Glutamate, etc."}, "brain_region": {"type": "string", "description": "The region of the brain to consider.", "default": "All"}}, "required": ["neuron_type", "brain_region"]}}]
|
[{"type": "function", "function": {"name": "get_neuron_coordinates", "description": "Retrieve the coordinates of the specified neuron in the rat's brain. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"neuron_type": {"type": "string", "description": "Type of neuron to find. For instance, GABA, Glutamate, etc."}, "brain_region": {"type": "string", "description": "The region of the brain to consider.", "default": "All"}}, "required": ["neuron_type", "brain_region"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_neuron_coordinates', 'description': \"Retrieve the coordinates of the specified neuron in the rat's brain. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'neuron_type': {'type': 'string', 'description': 'Type of neuron to find. For instance, GABA, Glutamate, etc.'}, 'brain_region': {'type': 'string', 'description': 'The region of the brain to consider.', 'default': 'All'}}, 'required': ['neuron_type', 'brain_region']}}]\n"}, {"role": "user", "content": "What are the coordinates of the neuron in a rat's all part of the brain that produces GABA neurotransmitters?"}]]
|
Python
|
simple
|
simple
|
[{"get_neuron_coordinates": {"neuron_type": ["GABA"], "brain_region": ["All", "all part of the brain", "entire brain"]}}]
|
simple_220
| false |
[{"name": "calculate_neuronal_activity", "description": "Calculate the neuronal activity (rate of firing) based on a given input synaptic rate, weight of inputs, and decay rate. Higher input or weight increases firing rate and higher decay rate decreases it.", "parameters": {"type": "dict", "properties": {"input_synaptic_rate": {"type": "integer", "description": "The synaptic input rate, usually represented as number of inputs per second."}, "weight": {"type": "float", "description": "The weight of the input, denoting its influence on the neuron's state. Default is 1.0."}, "decay_rate": {"type": "float", "description": "The rate at which the neuron's potential decays in the absence of inputs."}}, "required": ["input_synaptic_rate", "decay_rate"]}}]
|
[{"type": "function", "function": {"name": "calculate_neuronal_activity", "description": "Calculate the neuronal activity (rate of firing) based on a given input synaptic rate, weight of inputs, and decay rate. Higher input or weight increases firing rate and higher decay rate decreases it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"input_synaptic_rate": {"type": "integer", "description": "The synaptic input rate, usually represented as number of inputs per second."}, "weight": {"type": "number", "description": "The weight of the input, denoting its influence on the neuron's state. Default is 1.0. This is a float type value.", "format": "float"}, "decay_rate": {"type": "number", "description": "The rate at which the neuron's potential decays in the absence of inputs. This is a float type value.", "format": "float"}}, "required": ["input_synaptic_rate", "decay_rate"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_neuronal_activity', 'description': 'Calculate the neuronal activity (rate of firing) based on a given input synaptic rate, weight of inputs, and decay rate. Higher input or weight increases firing rate and higher decay rate decreases it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'input_synaptic_rate': {'type': 'integer', 'description': 'The synaptic input rate, usually represented as number of inputs per second.'}, 'weight': {'type': 'float', 'description': \"The weight of the input, denoting its influence on the neuron's state. Default is 1.0.\"}, 'decay_rate': {'type': 'float', 'description': \"The rate at which the neuron's potential decays in the absence of inputs.\"}}, 'required': ['input_synaptic_rate', 'decay_rate']}}]\n"}, {"role": "user", "content": "Calculate the neuronal activity based on synaptic input rate of 200 and weight 0.5 and decay rate of 0.1."}]]
|
Python
|
simple
|
simple
|
[{"calculate_neuronal_activity": {"input_synaptic_rate": [200], "weight": [0.5], "decay_rate": [0.1]}}]
|
simple_221
| false |
[{"name": "population_growth_estimate", "description": "Estimate the future population growth of a specific location over a specified time period.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city that you want to estimate the population growth for."}, "years": {"type": "integer", "description": "Number of years into the future for the estimate."}, "rate": {"type": "float", "description": "Expected annual growth rate in percentage. Default is 1.2."}}, "required": ["location", "years"]}}]
|
[{"type": "function", "function": {"name": "population_growth_estimate", "description": "Estimate the future population growth of a specific location over a specified time period. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city that you want to estimate the population growth for."}, "years": {"type": "integer", "description": "Number of years into the future for the estimate."}, "rate": {"type": "number", "description": "Expected annual growth rate in percentage. Default is 1.2. This is a float type value.", "format": "float"}}, "required": ["location", "years"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'population_growth_estimate', 'description': 'Estimate the future population growth of a specific location over a specified time period. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city that you want to estimate the population growth for.'}, 'years': {'type': 'integer', 'description': 'Number of years into the future for the estimate.'}, 'rate': {'type': 'float', 'description': 'Expected annual growth rate in percentage. Default is 1.2.'}}, 'required': ['location', 'years']}}]\n"}, {"role": "user", "content": "What will be the population growth in London over the next five years?"}]]
|
Python
|
simple
|
simple
|
[{"population_growth_estimate": {"location": ["London"], "years": [5], "rate": ["", 1.2]}}]
|
simple_222
| false |
[{"name": "calculate_bmi", "description": "Calculate the Body Mass Index based on given weight and height.", "parameters": {"type": "dict", "properties": {"weight": {"type": "integer", "description": "The weight of a person in kilograms."}, "height": {"type": "integer", "description": "The height of a person in centimeters."}, "unit": {"type": "string", "description": "Optional. The measurement system to be used for the result. The default is 'metric'."}}, "required": ["weight", "height"]}}]
|
[{"type": "function", "function": {"name": "calculate_bmi", "description": "Calculate the Body Mass Index based on given weight and height. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"weight": {"type": "integer", "description": "The weight of a person in kilograms."}, "height": {"type": "integer", "description": "The height of a person in centimeters."}, "unit": {"type": "string", "description": "Optional. The measurement system to be used for the result. The default is 'metric'."}}, "required": ["weight", "height"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_bmi', 'description': 'Calculate the Body Mass Index based on given weight and height. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'weight': {'type': 'integer', 'description': 'The weight of a person in kilograms.'}, 'height': {'type': 'integer', 'description': 'The height of a person in centimeters.'}, 'unit': {'type': 'string', 'description': \"Optional. The measurement system to be used for the result. The default is 'metric'.\"}}, 'required': ['weight', 'height']}}]\n"}, {"role": "user", "content": "Can you calculate my Body Mass Index (BMI) given my weight is 70 kg and height is 180 cm?"}]]
|
Python
|
simple
|
simple
|
[{"calculate_bmi": {"weight": [70], "height": [180], "unit": ["", "metric"]}}]
|
simple_223
| false |
[{"name": "group_dynamics.pattern", "description": "Examine the social dynamics and interactions within a group based on the personality traits and group size.", "parameters": {"type": "dict", "properties": {"total": {"type": "integer", "description": "The total group size."}, "extroverts": {"type": "integer", "description": "The number of extroverted members in the group."}, "introverts": {"type": "integer", "description": "The number of introverted members in the group."}}, "required": ["total", "extroverts", "introverts"]}}]
|
[{"type": "function", "function": {"name": "group_dynamics_pattern", "description": "Examine the social dynamics and interactions within a group based on the personality traits and group size. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"total": {"type": "integer", "description": "The total group size."}, "extroverts": {"type": "integer", "description": "The number of extroverted members in the group."}, "introverts": {"type": "integer", "description": "The number of introverted members in the group."}}, "required": ["total", "extroverts", "introverts"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'group_dynamics.pattern', 'description': 'Examine the social dynamics and interactions within a group based on the personality traits and group size. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'total': {'type': 'integer', 'description': 'The total group size.'}, 'extroverts': {'type': 'integer', 'description': 'The number of extroverted members in the group.'}, 'introverts': {'type': 'integer', 'description': 'The number of introverted members in the group.'}}, 'required': ['total', 'extroverts', 'introverts']}}]\n"}, {"role": "user", "content": "Find social behaviors and patterns in a group size of 50 with extroverted members being 15 and introverted members being 35."}]]
|
Python
|
simple
|
simple
|
[{"group_dynamics.pattern": {"total": [50], "extroverts": [15], "introverts": [35]}}]
|
simple_224
| false |
[{"name": "social_media_analytics.most_followed", "description": "Find the most followed Twitter user related to certain topics.", "parameters": {"type": "dict", "properties": {"topic": {"type": "string", "description": "The main topic of interest."}, "sub_topics": {"type": "array", "items": {"type": "string"}, "description": "Sub-topics related to main topic. Default is empty."}, "region": {"type": "string", "description": "Region of interest for twitter search. Default is 'all'."}}, "required": ["topic"]}}]
|
[{"type": "function", "function": {"name": "social_media_analytics_most_followed", "description": "Find the most followed Twitter user related to certain topics. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"topic": {"type": "string", "description": "The main topic of interest."}, "sub_topics": {"type": "array", "items": {"type": "string"}, "description": "Sub-topics related to main topic. Default is empty."}, "region": {"type": "string", "description": "Region of interest for twitter search. Default is 'all'."}}, "required": ["topic"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'social_media_analytics.most_followed', 'description': 'Find the most followed Twitter user related to certain topics. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'topic': {'type': 'string', 'description': 'The main topic of interest.'}, 'sub_topics': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Sub-topics related to main topic. Default is empty.'}, 'region': {'type': 'string', 'description': \"Region of interest for twitter search. Default is 'all'.\"}}, 'required': ['topic']}}]\n"}, {"role": "user", "content": "Find the most followed person on twitter who tweets about psychology related to behaviour and group dynamics."}]]
|
Python
|
simple
|
simple
|
[{"social_media_analytics.most_followed": {"topic": ["psychology"], "sub_topics": [["behaviour", "group dynamics"]], "region": ["", "all"]}}]
|
simple_225
| false |
[{"name": "psych_research.get_preference", "description": "Gathers research data on public preference between two options, based on societal category.", "parameters": {"type": "dict", "properties": {"category": {"type": "string", "description": "The societal category the preference data is about. E.g. reading, transportation, food"}, "option_one": {"type": "string", "description": "The first option people could prefer."}, "option_two": {"type": "string", "description": "The second option people could prefer."}, "demographic": {"type": "string", "description": "Specific demographic of society to narrow down the research.", "default": "all"}}, "required": ["category", "option_one", "option_two"]}}]
|
[{"type": "function", "function": {"name": "psych_research_get_preference", "description": "Gathers research data on public preference between two options, based on societal category. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"category": {"type": "string", "description": "The societal category the preference data is about. E.g. reading, transportation, food"}, "option_one": {"type": "string", "description": "The first option people could prefer."}, "option_two": {"type": "string", "description": "The second option people could prefer."}, "demographic": {"type": "string", "description": "Specific demographic of society to narrow down the research.", "default": "all"}}, "required": ["category", "option_one", "option_two"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'psych_research.get_preference', 'description': 'Gathers research data on public preference between two options, based on societal category. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'category': {'type': 'string', 'description': 'The societal category the preference data is about. E.g. reading, transportation, food'}, 'option_one': {'type': 'string', 'description': 'The first option people could prefer.'}, 'option_two': {'type': 'string', 'description': 'The second option people could prefer.'}, 'demographic': {'type': 'string', 'description': 'Specific demographic of society to narrow down the research.', 'default': 'all'}}, 'required': ['category', 'option_one', 'option_two']}}]\n"}, {"role": "user", "content": "What is the percentage of population preferring digital reading over physical books?"}]]
|
Python
|
simple
|
simple
|
[{"psych_research.get_preference": {"category": ["reading"], "option_one": ["digital reading", "digital"], "option_two": ["physical book", "physical", "physical books"], "demographic": ["", "all"]}}]
|
simple_226
| false |
[{"name": "get_zodiac_compatibility", "description": "Retrieve the compatibility score between two Zodiac signs.", "parameters": {"type": "dict", "properties": {"sign1": {"type": "string", "description": "The first Zodiac sign."}, "sign2": {"type": "string", "description": "The second Zodiac sign."}, "scale": {"type": "string", "enum": ["percentage", "0-10 scale"], "description": "The scale on which compatibility should be shown. Default is 'percentage'."}}, "required": ["sign1", "sign2"]}}]
|
[{"type": "function", "function": {"name": "get_zodiac_compatibility", "description": "Retrieve the compatibility score between two Zodiac signs. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"sign1": {"type": "string", "description": "The first Zodiac sign."}, "sign2": {"type": "string", "description": "The second Zodiac sign."}, "scale": {"type": "string", "enum": ["percentage", "0-10 scale"], "description": "The scale on which compatibility should be shown. Default is 'percentage'."}}, "required": ["sign1", "sign2"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_zodiac_compatibility', 'description': 'Retrieve the compatibility score between two Zodiac signs. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'sign1': {'type': 'string', 'description': 'The first Zodiac sign.'}, 'sign2': {'type': 'string', 'description': 'The second Zodiac sign.'}, 'scale': {'type': 'string', 'enum': ['percentage', '0-10 scale'], 'description': \"The scale on which compatibility should be shown. Default is 'percentage'.\"}}, 'required': ['sign1', 'sign2']}}]\n"}, {"role": "user", "content": "Find the compatibility score in percentage of Aries with Gemini."}]]
|
Python
|
simple
|
simple
|
[{"get_zodiac_compatibility": {"sign1": ["Aries"], "sign2": ["Gemini"], "scale": ["percentage", ""]}}]
|
simple_227
| false |
[{"name": "get_personality_traits", "description": "Retrieve the personality traits for a specific personality type, including their strengths and weaknesses.", "parameters": {"type": "dict", "properties": {"type": {"type": "string", "description": "The personality type."}, "traits": {"type": "array", "items": {"type": "string", "enum": ["strengths", "weaknesses"]}, "description": "List of traits to be retrieved, default is ['strengths']."}}, "required": ["type"]}}]
|
[{"type": "function", "function": {"name": "get_personality_traits", "description": "Retrieve the personality traits for a specific personality type, including their strengths and weaknesses. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"type": {"type": "string", "description": "The personality type."}, "traits": {"type": "array", "items": {"type": "string", "enum": ["strengths", "weaknesses"]}, "description": "List of traits to be retrieved, default is ['strengths']."}}, "required": ["type"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_personality_traits', 'description': 'Retrieve the personality traits for a specific personality type, including their strengths and weaknesses. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'type': {'type': 'string', 'description': 'The personality type.'}, 'traits': {'type': 'array', 'items': {'type': 'string', 'enum': ['strengths', 'weaknesses']}, 'description': \"List of traits to be retrieved, default is ['strengths'].\"}}, 'required': ['type']}}]\n"}, {"role": "user", "content": "Get me strength and weakness traits for ENFJ personality type."}]]
|
Python
|
simple
|
simple
|
[{"get_personality_traits": {"type": ["ENFJ"], "traits": [["strengths", "weaknesses"]]}}]
|
simple_228
| false |
[{"name": "get_personality_traits", "description": "Retrieve the common personality traits of people based on their hobbies or activities.", "parameters": {"type": "dict", "properties": {"hobby": {"type": "string", "description": "The hobby or activity of interest."}, "trait_count": {"type": "integer", "description": "The number of top traits to return, default is 5"}}, "required": ["hobby"]}}]
|
[{"type": "function", "function": {"name": "get_personality_traits", "description": "Retrieve the common personality traits of people based on their hobbies or activities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"hobby": {"type": "string", "description": "The hobby or activity of interest."}, "trait_count": {"type": "integer", "description": "The number of top traits to return, default is 5"}}, "required": ["hobby"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_personality_traits', 'description': 'Retrieve the common personality traits of people based on their hobbies or activities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'hobby': {'type': 'string', 'description': 'The hobby or activity of interest.'}, 'trait_count': {'type': 'integer', 'description': 'The number of top traits to return, default is 5'}}, 'required': ['hobby']}}]\n"}, {"role": "user", "content": "Find three personality traits of people who like jogging."}]]
|
Python
|
simple
|
simple
|
[{"get_personality_traits": {"hobby": ["jogging"], "trait_count": [3]}}]
|
simple_229
| false |
[{"name": "get_bigfive_scores", "description": "Retrieve Big Five Personality trait scores based on individual's behavioural characteristics.", "parameters": {"type": "dict", "properties": {"characteristics": {"type": "array", "items": {"type": "string"}, "description": "List of user's behavioural characteristics."}, "scale": {"type": "string", "enum": ["high", "medium", "low"], "description": "The scoring scale of traits (default is medium)."}}, "required": ["characteristics"]}}]
|
[{"type": "function", "function": {"name": "get_bigfive_scores", "description": "Retrieve Big Five Personality trait scores based on individual's behavioural characteristics. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"characteristics": {"type": "array", "items": {"type": "string"}, "description": "List of user's behavioural characteristics."}, "scale": {"type": "string", "enum": ["high", "medium", "low"], "description": "The scoring scale of traits (default is medium)."}}, "required": ["characteristics"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_bigfive_scores', 'description': \"Retrieve Big Five Personality trait scores based on individual's behavioural characteristics. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'characteristics': {'type': 'array', 'items': {'type': 'string'}, 'description': \"List of user's behavioural characteristics.\"}, 'scale': {'type': 'string', 'enum': ['high', 'medium', 'low'], 'description': 'The scoring scale of traits (default is medium).'}}, 'required': ['characteristics']}}]\n"}, {"role": "user", "content": "What's my Big Five Personality trait scores given that I am efficient, organized, easy going and compassionate?"}]]
|
Python
|
simple
|
simple
|
[{"get_bigfive_scores": {"characteristics": [["efficient", "organized", "easy going", "compassionate"]], "scale": ["medium", ""]}}]
|
simple_230
| false |
[{"name": "historic_leader_search", "description": "Retrieve information about a historical leader given a location and date.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The country or region in question."}, "date": {"type": "integer", "description": "The year being queried."}, "title": {"type": "string", "description": "The official title of the position. Default is 'King'."}}, "required": ["location", "date"]}}]
|
[{"type": "function", "function": {"name": "historic_leader_search", "description": "Retrieve information about a historical leader given a location and date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The country or region in question."}, "date": {"type": "integer", "description": "The year being queried."}, "title": {"type": "string", "description": "The official title of the position. Default is 'King'."}}, "required": ["location", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'historic_leader_search', 'description': 'Retrieve information about a historical leader given a location and date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The country or region in question.'}, 'date': {'type': 'integer', 'description': 'The year being queried.'}, 'title': {'type': 'string', 'description': \"The official title of the position. Default is 'King'.\"}}, 'required': ['location', 'date']}}]\n"}, {"role": "user", "content": "Who was the King of France in 1510?"}]]
|
Python
|
simple
|
simple
|
[{"historic_leader_search": {"location": ["France"], "date": [1510], "title": ["King", ""]}}]
|
simple_231
| false |
[{"name": "history.get_key_events", "description": "Retrieve key historical events within a specific period for a certain country.", "parameters": {"type": "dict", "properties": {"country": {"type": "string", "description": "The name of the country for which history is queried."}, "start_year": {"type": "integer", "description": "Start year of the period for which history is queried."}, "end_year": {"type": "integer", "description": "End year of the period for which history is queried."}, "event_type": {"type": "array", "items": {"type": "string", "enum": ["War", "Revolutions", "Diplomacy", "Economy"]}, "description": "Types of event. Default to 'all', which all types will be considered."}}, "required": ["country", "start_year", "end_year"]}}]
|
[{"type": "function", "function": {"name": "history_get_key_events", "description": "Retrieve key historical events within a specific period for a certain country. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"country": {"type": "string", "description": "The name of the country for which history is queried."}, "start_year": {"type": "integer", "description": "Start year of the period for which history is queried."}, "end_year": {"type": "integer", "description": "End year of the period for which history is queried."}, "event_type": {"type": "array", "items": {"type": "string", "enum": ["War", "Revolutions", "Diplomacy", "Economy"]}, "description": "Types of event. Default to 'all', which all types will be considered."}}, "required": ["country", "start_year", "end_year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'history.get_key_events', 'description': 'Retrieve key historical events within a specific period for a certain country. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'country': {'type': 'string', 'description': 'The name of the country for which history is queried.'}, 'start_year': {'type': 'integer', 'description': 'Start year of the period for which history is queried.'}, 'end_year': {'type': 'integer', 'description': 'End year of the period for which history is queried.'}, 'event_type': {'type': 'array', 'items': {'type': 'string', 'enum': ['War', 'Revolutions', 'Diplomacy', 'Economy']}, 'description': \"Types of event. Default to 'all', which all types will be considered.\"}}, 'required': ['country', 'start_year', 'end_year']}}]\n"}, {"role": "user", "content": "Provide key war events in German history from 1871 to 1945."}]]
|
Python
|
simple
|
simple
|
[{"history.get_key_events": {"country": ["Germany", "DE"], "start_year": [1871], "end_year": [1945], "event_type": [["War"]]}}]
|
simple_232
| false |
[{"name": "monarch.getMonarchOfYear", "description": "Retrieve the monarch of a specific location during a specified year.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The location (e.g., country) whose monarch needs to be found."}, "year": {"type": "integer", "description": "The year to search the monarch."}, "fullName": {"type": "boolean", "default": false, "description": "If true, returns the full name and title of the monarch."}}, "required": ["location", "year"]}}]
|
[{"type": "function", "function": {"name": "monarch_getMonarchOfYear", "description": "Retrieve the monarch of a specific location during a specified year. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The location (e.g., country) whose monarch needs to be found."}, "year": {"type": "integer", "description": "The year to search the monarch."}, "fullName": {"type": "boolean", "default": false, "description": "If true, returns the full name and title of the monarch."}}, "required": ["location", "year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'monarch.getMonarchOfYear', 'description': 'Retrieve the monarch of a specific location during a specified year. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The location (e.g., country) whose monarch needs to be found.'}, 'year': {'type': 'integer', 'description': 'The year to search the monarch.'}, 'fullName': {'type': 'boolean', 'default': False, 'description': 'If true, returns the full name and title of the monarch.'}}, 'required': ['location', 'year']}}]\n"}, {"role": "user", "content": "What was the full name king of England in 1800?"}]]
|
Python
|
simple
|
simple
|
[{"monarch.getMonarchOfYear": {"location": ["England", "ENG"], "year": [1800], "fullName": [true]}}]
|
simple_233
| false |
[{"name": "european_history.get_event_date", "description": "Retrieve the date of a specific event in European history.", "parameters": {"type": "dict", "properties": {"event_name": {"type": "string", "description": "The name of the event."}, "format": {"type": "string", "description": "Optional format of the returned date. Default is 'MM-DD-YYYY'."}}, "required": ["event_name"]}}]
|
[{"type": "function", "function": {"name": "european_history_get_event_date", "description": "Retrieve the date of a specific event in European history. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"event_name": {"type": "string", "description": "The name of the event."}, "format": {"type": "string", "description": "Optional format of the returned date. Default is 'MM-DD-YYYY'."}}, "required": ["event_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'european_history.get_event_date', 'description': 'Retrieve the date of a specific event in European history. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'event_name': {'type': 'string', 'description': 'The name of the event.'}, 'format': {'type': 'string', 'description': \"Optional format of the returned date. Default is 'MM-DD-YYYY'.\"}}, 'required': ['event_name']}}]\n"}, {"role": "user", "content": "When did the Treaty of Tordesillas take place? Put it in the format of YYYY."}]]
|
Python
|
simple
|
simple
|
[{"european_history.get_event_date": {"event_name": ["Treaty of Tordesillas"], "format": ["YYYY"]}}]
|
simple_234
| false |
[{"name": "history_eu.fetch_events", "description": "Fetches significant historical events within a specific time period in European history.", "parameters": {"type": "dict", "properties": {"century": {"type": "integer", "description": "The century you are interested in."}, "region": {"type": "string", "description": "The region of Europe you are interested in.", "enum": ["Northern", "Southern", "Eastern", "Western"]}, "category": {"type": "string", "description": "Category of the historical events. Default is 'Culture'.", "enum": ["Wars", "Culture", "Politics", "Scientific", "Others"]}}, "required": ["century", "region"]}}]
|
[{"type": "function", "function": {"name": "history_eu_fetch_events", "description": "Fetches significant historical events within a specific time period in European history. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"century": {"type": "integer", "description": "The century you are interested in."}, "region": {"type": "string", "description": "The region of Europe you are interested in.", "enum": ["Northern", "Southern", "Eastern", "Western"]}, "category": {"type": "string", "description": "Category of the historical events. Default is 'Culture'.", "enum": ["Wars", "Culture", "Politics", "Scientific", "Others"]}}, "required": ["century", "region"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'history_eu.fetch_events', 'description': 'Fetches significant historical events within a specific time period in European history. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'century': {'type': 'integer', 'description': 'The century you are interested in.'}, 'region': {'type': 'string', 'description': 'The region of Europe you are interested in.', 'enum': ['Northern', 'Southern', 'Eastern', 'Western']}, 'category': {'type': 'string', 'description': \"Category of the historical events. Default is 'Culture'.\", 'enum': ['Wars', 'Culture', 'Politics', 'Scientific', 'Others']}}, 'required': ['century', 'region']}}]\n"}, {"role": "user", "content": "Find important Wars in European history during the 19th century."}]]
|
Python
|
simple
|
simple
|
[{"history_eu.fetch_events": {"century": [19], "region": ["Northern", "Southern", "Eastern", "Western"], "category": ["Wars"]}}]
|
simple_235
| false |
[{"name": "get_event_date", "description": "Retrieve the date of a historical event.", "parameters": {"type": "dict", "properties": {"event": {"type": "string", "description": "The name of the historical event."}, "location": {"type": "string", "description": "Location where the event took place. Default to global if not specified."}}, "required": ["event"]}}]
|
[{"type": "function", "function": {"name": "get_event_date", "description": "Retrieve the date of a historical event. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"event": {"type": "string", "description": "The name of the historical event."}, "location": {"type": "string", "description": "Location where the event took place. Default to global if not specified."}}, "required": ["event"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_event_date', 'description': 'Retrieve the date of a historical event. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'event': {'type': 'string', 'description': 'The name of the historical event.'}, 'location': {'type': 'string', 'description': 'Location where the event took place. Default to global if not specified.'}}, 'required': ['event']}}]\n"}, {"role": "user", "content": "When was the signing of the Treaty of Lisbon?"}]]
|
Python
|
simple
|
simple
|
[{"get_event_date": {"event": ["Treaty of Lisbon", "Signing of the Treaty of Lisbon", "The signing of the Treaty of Lisbon"], "location": ["", "Lisbon", "Lisbon, Portugal"]}}]
|
simple_236
| false |
[{"name": "us_history.get_event_info", "description": "Retrieve detailed information about a significant event in U.S. history.", "parameters": {"type": "dict", "properties": {"event_name": {"type": "string", "description": "The name of the event."}, "specific_info": {"type": "string", "description": "Specific aspect of information related to event.", "enum": ["Start Date", "End Date", "Participants", "Result", "Notable Figures", "Importance in History"]}}, "required": ["event_name", "specific_info"]}}]
|
[{"type": "function", "function": {"name": "us_history_get_event_info", "description": "Retrieve detailed information about a significant event in U.S. history. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"event_name": {"type": "string", "description": "The name of the event."}, "specific_info": {"type": "string", "description": "Specific aspect of information related to event.", "enum": ["Start Date", "End Date", "Participants", "Result", "Notable Figures", "Importance in History"]}}, "required": ["event_name", "specific_info"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'us_history.get_event_info', 'description': 'Retrieve detailed information about a significant event in U.S. history. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'event_name': {'type': 'string', 'description': 'The name of the event.'}, 'specific_info': {'type': 'string', 'description': 'Specific aspect of information related to event.', 'enum': ['Start Date', 'End Date', 'Participants', 'Result', 'Notable Figures', 'Importance in History']}}, 'required': ['event_name', 'specific_info']}}]\n"}, {"role": "user", "content": "Get start date on the American Civil War."}]]
|
Python
|
simple
|
simple
|
[{"us_history.get_event_info": {"event_name": ["American Civil War", "Civil War"], "specific_info": ["Start Date"]}}]
|
simple_237
| false |
[{"name": "get_historical_GDP", "description": "Retrieve historical GDP data for a specific country and time range.", "parameters": {"type": "dict", "properties": {"country": {"type": "string", "description": "The country for which the historical GDP data is required."}, "start_year": {"type": "integer", "description": "Starting year of the period for which GDP data is required."}, "end_year": {"type": "integer", "description": "Ending year of the period for which GDP data is required."}}, "required": ["country", "start_year", "end_year"]}}]
|
[{"type": "function", "function": {"name": "get_historical_GDP", "description": "Retrieve historical GDP data for a specific country and time range. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"country": {"type": "string", "description": "The country for which the historical GDP data is required."}, "start_year": {"type": "integer", "description": "Starting year of the period for which GDP data is required."}, "end_year": {"type": "integer", "description": "Ending year of the period for which GDP data is required."}}, "required": ["country", "start_year", "end_year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_historical_GDP', 'description': 'Retrieve historical GDP data for a specific country and time range. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'country': {'type': 'string', 'description': 'The country for which the historical GDP data is required.'}, 'start_year': {'type': 'integer', 'description': 'Starting year of the period for which GDP data is required.'}, 'end_year': {'type': 'integer', 'description': 'Ending year of the period for which GDP data is required.'}}, 'required': ['country', 'start_year', 'end_year']}}]\n"}, {"role": "user", "content": "Get historical GDP data for United States from 1960 to 2000."}]]
|
Python
|
simple
|
simple
|
[{"get_historical_GDP": {"country": ["United States", "US"], "start_year": [1960], "end_year": [2000]}}]
|
simple_238
| false |
[{"name": "us_history.get_president", "description": "Retrieve the U.S. president during a specific event in American history.", "parameters": {"type": "dict", "properties": {"event": {"type": "string", "description": "The event in U.S. history."}, "year": {"type": "integer", "description": "The specific year of the event."}}, "required": ["event", "year"]}}]
|
[{"type": "function", "function": {"name": "us_history_get_president", "description": "Retrieve the U.S. president during a specific event in American history. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"event": {"type": "string", "description": "The event in U.S. history."}, "year": {"type": "integer", "description": "The specific year of the event."}}, "required": ["event", "year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'us_history.get_president', 'description': 'Retrieve the U.S. president during a specific event in American history. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'event': {'type': 'string', 'description': 'The event in U.S. history.'}, 'year': {'type': 'integer', 'description': 'The specific year of the event.'}}, 'required': ['event', 'year']}}]\n"}, {"role": "user", "content": "Who was the president of the United States during the American Civil War?"}]]
|
Python
|
simple
|
simple
|
[{"us_history.get_president": {"event": ["American Civil War"], "year": [1861, 1862, 1863, 1864, 1865]}}]
|
simple_239
| false |
[{"name": "US_president.in_year", "description": "Retrieve the name of the U.S. president in a given year.", "parameters": {"type": "dict", "properties": {"year": {"type": "integer", "description": "The year in question."}, "full_name": {"type": "boolean", "default": true, "description": "Option to return full name with middle initial, if applicable."}}, "required": ["year"]}}]
|
[{"type": "function", "function": {"name": "US_president_in_year", "description": "Retrieve the name of the U.S. president in a given year. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"year": {"type": "integer", "description": "The year in question."}, "full_name": {"type": "boolean", "default": true, "description": "Option to return full name with middle initial, if applicable."}}, "required": ["year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'US_president.in_year', 'description': 'Retrieve the name of the U.S. president in a given year. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'year': {'type': 'integer', 'description': 'The year in question.'}, 'full_name': {'type': 'boolean', 'default': True, 'description': 'Option to return full name with middle initial, if applicable.'}}, 'required': ['year']}}]\n"}, {"role": "user", "content": "Who was the full name of the president of the United States in 1861?"}]]
|
Python
|
simple
|
simple
|
[{"US_president.in_year": {"year": [1861], "full_name": [true, ""]}}]
|
simple_240
| false |
[{"name": "history_api.get_president_by_year", "description": "Get the name of the U.S. President for a specified year.", "parameters": {"type": "dict", "properties": {"year": {"type": "integer", "description": "The year you want to know the U.S. president of."}, "full_term_only": {"type": "boolean", "description": "Flag to determine if we should only return presidents that served a full term for the specified year.", "default": false}}, "required": ["year"]}}]
|
[{"type": "function", "function": {"name": "history_api_get_president_by_year", "description": "Get the name of the U.S. President for a specified year. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"year": {"type": "integer", "description": "The year you want to know the U.S. president of."}, "full_term_only": {"type": "boolean", "description": "Flag to determine if we should only return presidents that served a full term for the specified year.", "default": false}}, "required": ["year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'history_api.get_president_by_year', 'description': 'Get the name of the U.S. President for a specified year. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'year': {'type': 'integer', 'description': 'The year you want to know the U.S. president of.'}, 'full_term_only': {'type': 'boolean', 'description': 'Flag to determine if we should only return presidents that served a full term for the specified year.', 'default': False}}, 'required': ['year']}}]\n"}, {"role": "user", "content": "Who was the President of the United States in 1940?"}]]
|
Python
|
simple
|
simple
|
[{"history_api.get_president_by_year": {"year": [1940], "full_term_only": ["", true, false]}}]
|
simple_241
| false |
[{"name": "US_President_During_Event", "description": "Returns the U.S. president during a specified historical event.", "parameters": {"type": "dict", "properties": {"event": {"type": "string", "description": "The historical event."}, "country": {"type": "string", "description": "The country the president leads (optional parameter, defaults to 'USA' if not specified)."}}, "required": ["event"]}}]
|
[{"type": "function", "function": {"name": "US_President_During_Event", "description": "Returns the U.S. president during a specified historical event. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"event": {"type": "string", "description": "The historical event."}, "country": {"type": "string", "description": "The country the president leads (optional parameter, defaults to 'USA' if not specified)."}}, "required": ["event"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'US_President_During_Event', 'description': 'Returns the U.S. president during a specified historical event. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'event': {'type': 'string', 'description': 'The historical event.'}, 'country': {'type': 'string', 'description': \"The country the president leads (optional parameter, defaults to 'USA' if not specified).\"}}, 'required': ['event']}}]\n"}, {"role": "user", "content": "Who was the U.S. president during the Civil War?"}]]
|
Python
|
simple
|
simple
|
[{"US_President_During_Event": {"event": ["Civil War"], "country": ["USA", ""]}}]
|
simple_242
| false |
[{"name": "get_scientist_for_discovery", "description": "Retrieve the scientist's name who is credited for a specific scientific discovery or theory.", "parameters": {"type": "dict", "properties": {"discovery": {"type": "string", "description": "The scientific discovery or theory."}}, "required": ["discovery"]}}]
|
[{"type": "function", "function": {"name": "get_scientist_for_discovery", "description": "Retrieve the scientist's name who is credited for a specific scientific discovery or theory. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"discovery": {"type": "string", "description": "The scientific discovery or theory."}}, "required": ["discovery"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_scientist_for_discovery', 'description': \"Retrieve the scientist's name who is credited for a specific scientific discovery or theory. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'discovery': {'type': 'string', 'description': 'The scientific discovery or theory.'}}, 'required': ['discovery']}}]\n"}, {"role": "user", "content": "Who is the scientist that first proposed the theory of evolution?"}]]
|
Python
|
simple
|
simple
|
[{"get_scientist_for_discovery": {"discovery": ["Theory of Evolution", "theory of evolution"]}}]
|
simple_243
| false |
[{"name": "get_discoverer", "description": "Get the person or team who made a particular scientific discovery", "parameters": {"type": "dict", "properties": {"discovery": {"type": "string", "description": "The discovery for which the discoverer's information is needed."}, "detail": {"type": "boolean", "description": "Optional flag to get additional details about the discoverer, such as birth date and nationality. Defaults to false."}}, "required": ["discovery", "detail"]}}]
|
[{"type": "function", "function": {"name": "get_discoverer", "description": "Get the person or team who made a particular scientific discovery Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"discovery": {"type": "string", "description": "The discovery for which the discoverer's information is needed."}, "detail": {"type": "boolean", "description": "Optional flag to get additional details about the discoverer, such as birth date and nationality. Defaults to false."}}, "required": ["discovery", "detail"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_discoverer', 'description': 'Get the person or team who made a particular scientific discovery Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'discovery': {'type': 'string', 'description': \"The discovery for which the discoverer's information is needed.\"}, 'detail': {'type': 'boolean', 'description': 'Optional flag to get additional details about the discoverer, such as birth date and nationality. Defaults to false.'}}, 'required': ['discovery', 'detail']}}]\n"}, {"role": "user", "content": "Who discovered the neutron? Give me detail information."}]]
|
Python
|
simple
|
simple
|
[{"get_discoverer": {"discovery": ["neutron"], "detail": [true]}}]
|
simple_244
| false |
[{"name": "publication_year.find", "description": "Fetches the year a particular scientific work was published.", "parameters": {"type": "dict", "properties": {"author": {"type": "string", "description": "Name of the author of the work."}, "work_title": {"type": "string", "description": "Title of the scientific work."}, "location": {"type": "string", "description": "Place of the publication, if known. Default to 'all'."}}, "required": ["author", "work_title"]}}]
|
[{"type": "function", "function": {"name": "publication_year_find", "description": "Fetches the year a particular scientific work was published. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"author": {"type": "string", "description": "Name of the author of the work."}, "work_title": {"type": "string", "description": "Title of the scientific work."}, "location": {"type": "string", "description": "Place of the publication, if known. Default to 'all'."}}, "required": ["author", "work_title"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'publication_year.find', 'description': 'Fetches the year a particular scientific work was published. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'author': {'type': 'string', 'description': 'Name of the author of the work.'}, 'work_title': {'type': 'string', 'description': 'Title of the scientific work.'}, 'location': {'type': 'string', 'description': \"Place of the publication, if known. Default to 'all'.\"}}, 'required': ['author', 'work_title']}}]\n"}, {"role": "user", "content": "What year was the law of universal gravitation published by Isaac Newton?"}]]
|
Python
|
simple
|
simple
|
[{"publication_year.find": {"author": ["Isaac Newton"], "work_title": ["Law of Universal Gravitation", "Universal Law of Gravitation", "The law of universal gravitation"], "location": ["", "all"]}}]
|
simple_245
| false |
[{"name": "discoverer.get", "description": "Retrieve the name of the discoverer of an element based on its name.", "parameters": {"type": "dict", "properties": {"element_name": {"type": "string", "description": "The name of the element."}, "year": {"type": "integer", "description": "Optional parameter that refers to the year of discovery. It could be helpful in case an element was discovered more than once. Default to 0, which means not use it."}, "first": {"type": "boolean", "default": true, "description": "Optional parameter indicating if the first discoverer's name should be retrieved."}}, "required": ["element_name"]}}]
|
[{"type": "function", "function": {"name": "discoverer_get", "description": "Retrieve the name of the discoverer of an element based on its name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"element_name": {"type": "string", "description": "The name of the element."}, "year": {"type": "integer", "description": "Optional parameter that refers to the year of discovery. It could be helpful in case an element was discovered more than once. Default to 0, which means not use it."}, "first": {"type": "boolean", "default": true, "description": "Optional parameter indicating if the first discoverer's name should be retrieved."}}, "required": ["element_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'discoverer.get', 'description': 'Retrieve the name of the discoverer of an element based on its name. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'element_name': {'type': 'string', 'description': 'The name of the element.'}, 'year': {'type': 'integer', 'description': 'Optional parameter that refers to the year of discovery. It could be helpful in case an element was discovered more than once. Default to 0, which means not use it.'}, 'first': {'type': 'boolean', 'default': True, 'description': \"Optional parameter indicating if the first discoverer's name should be retrieved.\"}}, 'required': ['element_name']}}]\n"}, {"role": "user", "content": "Who discovered radium?"}]]
|
Python
|
simple
|
simple
|
[{"discoverer.get": {"element_name": ["'radium'", "\"radium\"", "radium"], "year": ["", 0], "first": [true, ""]}}]
|
simple_246
| false |
[{"name": "science_history.get_discovery_details", "description": "Retrieve the details of a scientific discovery based on the discovery name.", "parameters": {"type": "dict", "properties": {"discovery": {"type": "string", "description": "The name of the discovery, e.g. Gravity"}, "method_used": {"type": "string", "description": "The method used for the discovery, default value is 'default' which gives the most accepted method."}}, "required": ["discovery"]}}]
|
[{"type": "function", "function": {"name": "science_history_get_discovery_details", "description": "Retrieve the details of a scientific discovery based on the discovery name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"discovery": {"type": "string", "description": "The name of the discovery, e.g. Gravity"}, "method_used": {"type": "string", "description": "The method used for the discovery, default value is 'default' which gives the most accepted method."}}, "required": ["discovery"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'science_history.get_discovery_details', 'description': 'Retrieve the details of a scientific discovery based on the discovery name. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'discovery': {'type': 'string', 'description': 'The name of the discovery, e.g. Gravity'}, 'method_used': {'type': 'string', 'description': \"The method used for the discovery, default value is 'default' which gives the most accepted method.\"}}, 'required': ['discovery']}}]\n"}, {"role": "user", "content": "Who discovered Gravity and what was the method used?"}]]
|
Python
|
simple
|
simple
|
[{"science_history.get_discovery_details": {"discovery": ["Gravity"], "method_used": ["", "default"]}}]
|
simple_247
| false |
[{"name": "historical_contrib.get_contrib", "description": "Retrieve historical contribution made by a scientist on a specific date.", "parameters": {"type": "dict", "properties": {"scientist": {"type": "string", "description": "The scientist whose contributions need to be searched."}, "date": {"type": "string", "description": "The date when the contribution was made in yyyy-mm-dd format."}, "category": {"type": "string", "description": "The field of the contribution, such as 'Physics' or 'Chemistry'. Default is 'all'."}}, "required": ["scientist", "date"]}}]
|
[{"type": "function", "function": {"name": "historical_contrib_get_contrib", "description": "Retrieve historical contribution made by a scientist on a specific date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"scientist": {"type": "string", "description": "The scientist whose contributions need to be searched."}, "date": {"type": "string", "description": "The date when the contribution was made in yyyy-mm-dd format."}, "category": {"type": "string", "description": "The field of the contribution, such as 'Physics' or 'Chemistry'. Default is 'all'."}}, "required": ["scientist", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'historical_contrib.get_contrib', 'description': 'Retrieve historical contribution made by a scientist on a specific date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'scientist': {'type': 'string', 'description': 'The scientist whose contributions need to be searched.'}, 'date': {'type': 'string', 'description': 'The date when the contribution was made in yyyy-mm-dd format.'}, 'category': {'type': 'string', 'description': \"The field of the contribution, such as 'Physics' or 'Chemistry'. Default is 'all'.\"}}, 'required': ['scientist', 'date']}}]\n"}, {"role": "user", "content": "What was Albert Einstein's contribution to science on March 17, 1915?"}]]
|
Python
|
simple
|
simple
|
[{"historical_contrib.get_contrib": {"scientist": ["Albert Einstein"], "date": ["1915-03-17", "03/17/1915", "Mar.17,1915"], "category": ["", "all"]}}]
|
simple_248
| false |
[{"name": "science_history.get_invention", "description": "Retrieve the inventor and year of invention based on the invention's name.", "parameters": {"type": "dict", "properties": {"invention_name": {"type": "string", "description": "The name of the invention."}, "want_year": {"type": "boolean", "default": false, "description": "Return the year of invention if set to true."}}, "required": ["invention_name", "want_year"]}}]
|
[{"type": "function", "function": {"name": "science_history_get_invention", "description": "Retrieve the inventor and year of invention based on the invention's name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"invention_name": {"type": "string", "description": "The name of the invention."}, "want_year": {"type": "boolean", "default": false, "description": "Return the year of invention if set to true."}}, "required": ["invention_name", "want_year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'science_history.get_invention', 'description': \"Retrieve the inventor and year of invention based on the invention's name. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'invention_name': {'type': 'string', 'description': 'The name of the invention.'}, 'want_year': {'type': 'boolean', 'default': False, 'description': 'Return the year of invention if set to true.'}}, 'required': ['invention_name', 'want_year']}}]\n"}, {"role": "user", "content": "Who invented the theory of relativity and in which year?"}]]
|
Python
|
simple
|
simple
|
[{"science_history.get_invention": {"invention_name": ["theory of relativity", "Theory of Relativity"], "want_year": [true]}}]
|
simple_249
| false |
[{"name": "religion.history_info", "description": "Provides comprehensive historical details about a specified religion till a specified century.", "parameters": {"type": "dict", "properties": {"religion": {"type": "string", "description": "The name of the religion for which historical details are needed."}, "till_century": {"type": "integer", "description": "The century till which historical details are needed."}, "include_people": {"type": "boolean", "description": "To include influential people related to the religion during that time period, default is False"}}, "required": ["religion", "till_century"]}}]
|
[{"type": "function", "function": {"name": "religion_history_info", "description": "Provides comprehensive historical details about a specified religion till a specified century. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"religion": {"type": "string", "description": "The name of the religion for which historical details are needed."}, "till_century": {"type": "integer", "description": "The century till which historical details are needed."}, "include_people": {"type": "boolean", "description": "To include influential people related to the religion during that time period, default is False"}}, "required": ["religion", "till_century"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'religion.history_info', 'description': 'Provides comprehensive historical details about a specified religion till a specified century. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'religion': {'type': 'string', 'description': 'The name of the religion for which historical details are needed.'}, 'till_century': {'type': 'integer', 'description': 'The century till which historical details are needed.'}, 'include_people': {'type': 'boolean', 'description': 'To include influential people related to the religion during that time period, default is False'}}, 'required': ['religion', 'till_century']}}]\n"}, {"role": "user", "content": "Tell me more about Christianity and its history till the 14th century"}]]
|
Python
|
simple
|
simple
|
[{"religion.history_info": {"religion": ["Christianity"], "till_century": [14], "include_people": [false, ""]}}]
|
simple_250
| false |
[{"name": "get_time_difference", "description": "Get the time difference between two places.", "parameters": {"type": "dict", "properties": {"place1": {"type": "string", "description": "The first place for time difference."}, "place2": {"type": "string", "description": "The second place for time difference."}}, "required": ["place1", "place2"]}}]
|
[{"type": "function", "function": {"name": "get_time_difference", "description": "Get the time difference between two places. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"place1": {"type": "string", "description": "The first place for time difference."}, "place2": {"type": "string", "description": "The second place for time difference."}}, "required": ["place1", "place2"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_time_difference', 'description': 'Get the time difference between two places. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'place1': {'type': 'string', 'description': 'The first place for time difference.'}, 'place2': {'type': 'string', 'description': 'The second place for time difference.'}}, 'required': ['place1', 'place2']}}]\n"}, {"role": "user", "content": "What's the time difference between San Francisco and Sydney?"}]]
|
Python
|
simple
|
simple
|
[{"get_time_difference": {"place1": ["San Francisco", "SF"], "place2": ["Sydney"]}}]
|
simple_251
| false |
[{"name": "get_earliest_reference", "description": "Retrieve the earliest historical reference of a person.", "parameters": {"type": "dict", "properties": {"name": {"type": "string", "description": "The name of the person."}, "source": {"type": "string", "enum": ["scriptures", "historical records"], "description": "Source to fetch the reference. Default is 'scriptures'"}}, "required": ["name"]}}]
|
[{"type": "function", "function": {"name": "get_earliest_reference", "description": "Retrieve the earliest historical reference of a person. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"name": {"type": "string", "description": "The name of the person."}, "source": {"type": "string", "enum": ["scriptures", "historical records"], "description": "Source to fetch the reference. Default is 'scriptures'"}}, "required": ["name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_earliest_reference', 'description': 'Retrieve the earliest historical reference of a person. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'name': {'type': 'string', 'description': 'The name of the person.'}, 'source': {'type': 'string', 'enum': ['scriptures', 'historical records'], 'description': \"Source to fetch the reference. Default is 'scriptures'\"}}, 'required': ['name']}}]\n"}, {"role": "user", "content": "What is the earliest reference of Jesus Christ in history from historical record?"}]]
|
Python
|
simple
|
simple
|
[{"get_earliest_reference": {"name": ["Jesus Christ"], "source": ["historical records"]}}]
|
simple_252
| false |
[{"name": "get_religion_history", "description": "Retrieves significant religious events, including the details of the event, its historical context, and its impacts.", "parameters": {"type": "dict", "properties": {"religion": {"type": "string", "description": "Name of the religion to be queried."}, "century": {"type": "integer", "description": "The century in which the event(s) took place."}, "sort_by": {"type": "string", "enum": ["importance", "chronological"], "default": "chronological", "description": "Order of sorting the events. Default is chronological."}, "count": {"type": "integer", "default": 5, "description": "Number of events to return. Default is 5."}}, "required": ["religion", "century"]}}]
|
[{"type": "function", "function": {"name": "get_religion_history", "description": "Retrieves significant religious events, including the details of the event, its historical context, and its impacts. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"religion": {"type": "string", "description": "Name of the religion to be queried."}, "century": {"type": "integer", "description": "The century in which the event(s) took place."}, "sort_by": {"type": "string", "enum": ["importance", "chronological"], "default": "chronological", "description": "Order of sorting the events. Default is chronological."}, "count": {"type": "integer", "default": 5, "description": "Number of events to return. Default is 5."}}, "required": ["religion", "century"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_religion_history', 'description': 'Retrieves significant religious events, including the details of the event, its historical context, and its impacts. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'religion': {'type': 'string', 'description': 'Name of the religion to be queried.'}, 'century': {'type': 'integer', 'description': 'The century in which the event(s) took place.'}, 'sort_by': {'type': 'string', 'enum': ['importance', 'chronological'], 'default': 'chronological', 'description': 'Order of sorting the events. Default is chronological.'}, 'count': {'type': 'integer', 'default': 5, 'description': 'Number of events to return. Default is 5.'}}, 'required': ['religion', 'century']}}]\n"}, {"role": "user", "content": "Find ten major historical events related to Christianity in the 16th century sort by importance."}]]
|
Python
|
simple
|
simple
|
[{"get_religion_history": {"religion": ["Christianity"], "century": [16], "sort_by": ["importance"], "count": [10]}}]
|
simple_253
| false |
[{"name": "retrieve_religion_info", "description": "Retrieve the history and main beliefs of a religion.", "parameters": {"type": "dict", "properties": {"religion_name": {"type": "string", "description": "The name of the religion."}, "detail_level": {"type": "string", "description": "Level of detail for the returned information, either 'summary' or 'full'.", "default": "summary"}}, "required": ["religion_name", "detail_level"]}}]
|
[{"type": "function", "function": {"name": "retrieve_religion_info", "description": "Retrieve the history and main beliefs of a religion. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"religion_name": {"type": "string", "description": "The name of the religion."}, "detail_level": {"type": "string", "description": "Level of detail for the returned information, either 'summary' or 'full'.", "default": "summary"}}, "required": ["religion_name", "detail_level"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'retrieve_religion_info', 'description': 'Retrieve the history and main beliefs of a religion. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'religion_name': {'type': 'string', 'description': 'The name of the religion.'}, 'detail_level': {'type': 'string', 'description': \"Level of detail for the returned information, either 'summary' or 'full'.\", 'default': 'summary'}}, 'required': ['religion_name', 'detail_level']}}]\n"}, {"role": "user", "content": "Retrieve the full historyof Buddhism"}]]
|
Python
|
simple
|
simple
|
[{"retrieve_religion_info": {"religion_name": ["Buddhism"], "detail_level": ["full"]}}]
|
simple_254
| false |
[{"name": "get_religion_history", "description": "Retrieves historic events and facts related to a specified religion for a given period.", "parameters": {"type": "dict", "properties": {"religion": {"type": "string", "description": "The name of the religion."}, "start_year": {"type": "integer", "description": "The starting year of the period."}, "end_year": {"type": "integer", "description": "The end year of the period."}, "event_type": {"type": "string", "enum": ["all", "crusade", "schism", "reform"], "description": "Optional parameter specifying the type of event. Default is 'all'."}}, "required": ["religion", "start_year", "end_year"]}}]
|
[{"type": "function", "function": {"name": "get_religion_history", "description": "Retrieves historic events and facts related to a specified religion for a given period. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"religion": {"type": "string", "description": "The name of the religion."}, "start_year": {"type": "integer", "description": "The starting year of the period."}, "end_year": {"type": "integer", "description": "The end year of the period."}, "event_type": {"type": "string", "enum": ["all", "crusade", "schism", "reform"], "description": "Optional parameter specifying the type of event. Default is 'all'."}}, "required": ["religion", "start_year", "end_year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_religion_history', 'description': 'Retrieves historic events and facts related to a specified religion for a given period. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'religion': {'type': 'string', 'description': 'The name of the religion.'}, 'start_year': {'type': 'integer', 'description': 'The starting year of the period.'}, 'end_year': {'type': 'integer', 'description': 'The end year of the period.'}, 'event_type': {'type': 'string', 'enum': ['all', 'crusade', 'schism', 'reform'], 'description': \"Optional parameter specifying the type of event. Default is 'all'.\"}}, 'required': ['religion', 'start_year', 'end_year']}}]\n"}, {"role": "user", "content": "Retrieve the historic dates and facts related to Christianity between year 300 and 400."}]]
|
Python
|
simple
|
simple
|
[{"get_religion_history": {"religion": ["Christianity"], "start_year": [300], "end_year": [400], "event_type": ["all", ""]}}]
|
simple_255
| false |
[{"name": "religious_history.get_papal_biography", "description": "Retrieve the biography and main religious and historical contributions of a Pope based on his papal name.", "parameters": {"type": "dict", "properties": {"papal_name": {"type": "string", "description": "The papal name of the Pope."}, "include_contributions": {"type": "boolean", "default": false, "description": "Include main contributions of the Pope in the response if true."}}, "required": ["papal_name", "include_contributions"]}}]
|
[{"type": "function", "function": {"name": "religious_history_get_papal_biography", "description": "Retrieve the biography and main religious and historical contributions of a Pope based on his papal name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"papal_name": {"type": "string", "description": "The papal name of the Pope."}, "include_contributions": {"type": "boolean", "default": false, "description": "Include main contributions of the Pope in the response if true."}}, "required": ["papal_name", "include_contributions"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'religious_history.get_papal_biography', 'description': 'Retrieve the biography and main religious and historical contributions of a Pope based on his papal name. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'papal_name': {'type': 'string', 'description': 'The papal name of the Pope.'}, 'include_contributions': {'type': 'boolean', 'default': False, 'description': 'Include main contributions of the Pope in the response if true.'}}, 'required': ['papal_name', 'include_contributions']}}]\n"}, {"role": "user", "content": "Get the biography and main contributions of Pope Innocent III."}]]
|
Python
|
simple
|
simple
|
[{"religious_history.get_papal_biography": {"papal_name": ["Innocent III", "Pope Innocent III"], "include_contributions": [true]}}]
|
simple_256
| false |
[{"name": "generate_circle_image", "description": "Generates a circle image based on the given radius and color", "parameters": {"type": "dict", "properties": {"radius": {"type": "integer", "description": "The radius of the circle in pixels."}, "color": {"type": "string", "description": "The color of the circle."}, "background": {"type": "string", "description": "Optional: The color of the background, default is white."}}, "required": ["radius", "color"]}}]
|
[{"type": "function", "function": {"name": "generate_circle_image", "description": "Generates a circle image based on the given radius and color Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"radius": {"type": "integer", "description": "The radius of the circle in pixels."}, "color": {"type": "string", "description": "The color of the circle."}, "background": {"type": "string", "description": "Optional: The color of the background, default is white."}}, "required": ["radius", "color"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'generate_circle_image', 'description': 'Generates a circle image based on the given radius and color Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'radius': {'type': 'integer', 'description': 'The radius of the circle in pixels.'}, 'color': {'type': 'string', 'description': 'The color of the circle.'}, 'background': {'type': 'string', 'description': 'Optional: The color of the background, default is white.'}}, 'required': ['radius', 'color']}}]\n"}, {"role": "user", "content": "Generate an image of a circle with a radius of 50 pixels and color 'Red'."}]]
|
Python
|
simple
|
simple
|
[{"generate_circle_image": {"radius": [50], "color": ["Red"], "background": ["", "white"]}}]
|
simple_257
| false |
[{"name": "identify_color_rgb", "description": "This function identifies the RGB values of a named color.", "parameters": {"type": "dict", "properties": {"color_name": {"type": "string", "description": "Name of the color."}, "standard": {"type": "string", "description": "The color standard (e.g. basic, pantone). Default is 'basic'"}}, "required": ["color_name"]}}]
|
[{"type": "function", "function": {"name": "identify_color_rgb", "description": "This function identifies the RGB values of a named color. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"color_name": {"type": "string", "description": "Name of the color."}, "standard": {"type": "string", "description": "The color standard (e.g. basic, pantone). Default is 'basic'"}}, "required": ["color_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'identify_color_rgb', 'description': 'This function identifies the RGB values of a named color. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'color_name': {'type': 'string', 'description': 'Name of the color.'}, 'standard': {'type': 'string', 'description': \"The color standard (e.g. basic, pantone). Default is 'basic'\"}}, 'required': ['color_name']}}]\n"}, {"role": "user", "content": "Can you help me identify the basic RGB value of Sea Green color?"}]]
|
Python
|
simple
|
simple
|
[{"identify_color_rgb": {"color_name": ["Sea Green"], "standard": ["basic", ""]}}]
|
simple_258
| false |
[{"name": "mix_paint_color", "description": "Combine two primary paint colors and adjust the resulting color's lightness level.", "parameters": {"type": "dict", "properties": {"color1": {"type": "string", "description": "The first primary color to be mixed."}, "color2": {"type": "string", "description": "The second primary color to be mixed."}, "lightness": {"type": "integer", "description": "The desired lightness level of the resulting color in percentage. The default level is set to 50."}}, "required": ["color1", "color2"]}}]
|
[{"type": "function", "function": {"name": "mix_paint_color", "description": "Combine two primary paint colors and adjust the resulting color's lightness level. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"color1": {"type": "string", "description": "The first primary color to be mixed."}, "color2": {"type": "string", "description": "The second primary color to be mixed."}, "lightness": {"type": "integer", "description": "The desired lightness level of the resulting color in percentage. The default level is set to 50."}}, "required": ["color1", "color2"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'mix_paint_color', 'description': \"Combine two primary paint colors and adjust the resulting color's lightness level. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'color1': {'type': 'string', 'description': 'The first primary color to be mixed.'}, 'color2': {'type': 'string', 'description': 'The second primary color to be mixed.'}, 'lightness': {'type': 'integer', 'description': 'The desired lightness level of the resulting color in percentage. The default level is set to 50.'}}, 'required': ['color1', 'color2']}}]\n"}, {"role": "user", "content": "Mix yellow and blue colors and adjust the lightness level to 60 percent."}]]
|
Python
|
simple
|
simple
|
[{"mix_paint_color": {"color1": ["yellow"], "color2": ["blue"], "lightness": [60]}}]
|
simple_259
| false |
[{"name": "calculate_paint_needed", "description": "Calculate the amount of paint needed to cover a surface area based on the coverage rate of a specific paint brand.", "parameters": {"type": "dict", "properties": {"coverage_rate": {"type": "integer", "description": "The area in square feet that one gallon of paint can cover."}, "length": {"type": "integer", "description": "Length of the wall to be painted in feet."}, "height": {"type": "integer", "description": "Height of the wall to be painted in feet."}}, "required": ["coverage_rate", "length", "height"]}}]
|
[{"type": "function", "function": {"name": "calculate_paint_needed", "description": "Calculate the amount of paint needed to cover a surface area based on the coverage rate of a specific paint brand. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"coverage_rate": {"type": "integer", "description": "The area in square feet that one gallon of paint can cover."}, "length": {"type": "integer", "description": "Length of the wall to be painted in feet."}, "height": {"type": "integer", "description": "Height of the wall to be painted in feet."}}, "required": ["coverage_rate", "length", "height"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_paint_needed', 'description': 'Calculate the amount of paint needed to cover a surface area based on the coverage rate of a specific paint brand. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'coverage_rate': {'type': 'integer', 'description': 'The area in square feet that one gallon of paint can cover.'}, 'length': {'type': 'integer', 'description': 'Length of the wall to be painted in feet.'}, 'height': {'type': 'integer', 'description': 'Height of the wall to be painted in feet.'}}, 'required': ['coverage_rate', 'length', 'height']}}]\n"}, {"role": "user", "content": "Calculate the total quantity of paint needed to cover a wall of 30 feet by 12 feet using a specific brand that covers 400 square feet per gallon."}]]
|
Python
|
simple
|
simple
|
[{"calculate_paint_needed": {"coverage_rate": [400], "length": [30], "height": [12]}}]
|
simple_260
| false |
[{"name": "paint_requirement.calculate", "description": "Calculate the amount of paint required to paint a given area. Account for coverage efficiency of the paint and exclusions (like windows).", "parameters": {"type": "dict", "properties": {"area": {"type": "dict", "properties": {"width": {"type": "integer", "description": "The width of the area to be painted in feet."}, "height": {"type": "integer", "description": "The height of the area to be painted in feet."}}, "description": "The area to be painted."}, "paint_coverage": {"type": "integer", "description": "Coverage area per gallon of the paint in square feet.", "default": 350}, "exclusion": {"type": "dict", "properties": {"type": {"type": "string", "description": "The type of the exclusion e.g window, door etc."}, "area": {"type": "integer", "description": "The area of the exclusion in square feet."}}, "description": "Area not to be painted. Default to not use any exclusion if not specified."}}, "required": ["area", "paint_coverage"]}}]
|
[{"type": "function", "function": {"name": "paint_requirement_calculate", "description": "Calculate the amount of paint required to paint a given area. Account for coverage efficiency of the paint and exclusions (like windows). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"area": {"type": "object", "properties": {"width": {"type": "integer", "description": "The width of the area to be painted in feet."}, "height": {"type": "integer", "description": "The height of the area to be painted in feet."}}, "description": "The area to be painted."}, "paint_coverage": {"type": "integer", "description": "Coverage area per gallon of the paint in square feet.", "default": 350}, "exclusion": {"type": "object", "properties": {"type": {"type": "string", "description": "The type of the exclusion e.g window, door etc."}, "area": {"type": "integer", "description": "The area of the exclusion in square feet."}}, "description": "Area not to be painted. Default to not use any exclusion if not specified."}}, "required": ["area", "paint_coverage"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'paint_requirement.calculate', 'description': 'Calculate the amount of paint required to paint a given area. Account for coverage efficiency of the paint and exclusions (like windows). Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'area': {'type': 'dict', 'properties': {'width': {'type': 'integer', 'description': 'The width of the area to be painted in feet.'}, 'height': {'type': 'integer', 'description': 'The height of the area to be painted in feet.'}}, 'description': 'The area to be painted.'}, 'paint_coverage': {'type': 'integer', 'description': 'Coverage area per gallon of the paint in square feet.', 'default': 350}, 'exclusion': {'type': 'dict', 'properties': {'type': {'type': 'string', 'description': 'The type of the exclusion e.g window, door etc.'}, 'area': {'type': 'integer', 'description': 'The area of the exclusion in square feet.'}}, 'description': 'Area not to be painted. Default to not use any exclusion if not specified.'}}, 'required': ['area', 'paint_coverage']}}]\n"}, {"role": "user", "content": "Calculate how many gallons of paint is required to paint a wall with width of 20ft and height of 12ft, assuming 1 gallon covers approximately 350 sq.ft. Don't include window area of 15 sq.ft."}]]
|
Python
|
simple
|
simple
|
[{"paint_requirement.calculate": {"area": [{"width": [20], "height": [12]}], "paint_coverage": [350], "exclusion": [{"type": ["window"], "area": [15]}]}}]
|
simple_261
| false |
[{"name": "draw_rectangle", "description": "Draw a rectangle given its width and height.", "parameters": {"type": "dict", "properties": {"width": {"type": "integer", "description": "The width of the rectangle."}, "height": {"type": "integer", "description": "The height of the rectangle."}, "color": {"type": "string", "description": "The color of the rectangle. Default is 'black'."}}, "required": ["width", "height"]}}]
|
[{"type": "function", "function": {"name": "draw_rectangle", "description": "Draw a rectangle given its width and height. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"width": {"type": "integer", "description": "The width of the rectangle."}, "height": {"type": "integer", "description": "The height of the rectangle."}, "color": {"type": "string", "description": "The color of the rectangle. Default is 'black'."}}, "required": ["width", "height"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'draw_rectangle', 'description': 'Draw a rectangle given its width and height. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'width': {'type': 'integer', 'description': 'The width of the rectangle.'}, 'height': {'type': 'integer', 'description': 'The height of the rectangle.'}, 'color': {'type': 'string', 'description': \"The color of the rectangle. Default is 'black'.\"}}, 'required': ['width', 'height']}}]\n"}, {"role": "user", "content": "Draw a rectangle with a width of 20 units and height of 10 units in red."}]]
|
Python
|
simple
|
simple
|
[{"draw_rectangle": {"width": [20], "height": [10], "color": ["red"]}}]
|
simple_262
| false |
[{"name": "modify_painting", "description": "Modify an existing painting's attributes such as size, medium, and color.", "parameters": {"type": "dict", "properties": {"size": {"type": "string", "description": "The size of the painting in inches, width by height."}, "medium": {"type": "string", "description": "The medium of the painting, such as oil, acrylic, etc."}, "dominant_color": {"type": "string", "description": "The dominant color of the painting. Default to 'black'."}}, "required": ["size", "medium"]}}]
|
[{"type": "function", "function": {"name": "modify_painting", "description": "Modify an existing painting's attributes such as size, medium, and color. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"size": {"type": "string", "description": "The size of the painting in inches, width by height."}, "medium": {"type": "string", "description": "The medium of the painting, such as oil, acrylic, etc."}, "dominant_color": {"type": "string", "description": "The dominant color of the painting. Default to 'black'."}}, "required": ["size", "medium"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'modify_painting', 'description': \"Modify an existing painting's attributes such as size, medium, and color. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'size': {'type': 'string', 'description': 'The size of the painting in inches, width by height.'}, 'medium': {'type': 'string', 'description': 'The medium of the painting, such as oil, acrylic, etc.'}, 'dominant_color': {'type': 'string', 'description': \"The dominant color of the painting. Default to 'black'.\"}}, 'required': ['size', 'medium']}}]\n"}, {"role": "user", "content": "Change my painting's medium to oil and change size to 12x18 with red dominant color."}]]
|
Python
|
simple
|
simple
|
[{"modify_painting": {"size": ["12x18"], "medium": ["oil"], "dominant_color": ["red"]}}]
|
simple_263
| false |
[{"name": "get_sculpture_info", "description": "Retrieves the most recent artwork by a specified artist with its detailed description.", "parameters": {"type": "dict", "properties": {"artist_name": {"type": "string", "description": "The name of the artist."}, "detail": {"type": "boolean", "description": "If True, it provides detailed description of the sculpture. Defaults to False."}}, "required": ["artist_name"]}}]
|
[{"type": "function", "function": {"name": "get_sculpture_info", "description": "Retrieves the most recent artwork by a specified artist with its detailed description. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist_name": {"type": "string", "description": "The name of the artist."}, "detail": {"type": "boolean", "description": "If True, it provides detailed description of the sculpture. Defaults to False."}}, "required": ["artist_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_sculpture_info', 'description': 'Retrieves the most recent artwork by a specified artist with its detailed description. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist_name': {'type': 'string', 'description': 'The name of the artist.'}, 'detail': {'type': 'boolean', 'description': 'If True, it provides detailed description of the sculpture. Defaults to False.'}}, 'required': ['artist_name']}}]\n"}, {"role": "user", "content": "Find me the most recent art sculpture by James Plensa with detailed description."}]]
|
Python
|
simple
|
simple
|
[{"get_sculpture_info": {"artist_name": ["James Plensa"], "detail": [true]}}]
|
simple_264
| false |
[{"name": "sculpture.get_details", "description": "Retrieve details of a sculpture based on the artist and the title of the sculpture.", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "The artist who made the sculpture."}, "title": {"type": "string", "description": "The title of the sculpture."}, "detail": {"type": "string", "description": "The specific detail wanted about the sculpture. Default is 'general information'."}}, "required": ["artist", "title"]}}]
|
[{"type": "function", "function": {"name": "sculpture_get_details", "description": "Retrieve details of a sculpture based on the artist and the title of the sculpture. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist": {"type": "string", "description": "The artist who made the sculpture."}, "title": {"type": "string", "description": "The title of the sculpture."}, "detail": {"type": "string", "description": "The specific detail wanted about the sculpture. Default is 'general information'."}}, "required": ["artist", "title"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sculpture.get_details', 'description': 'Retrieve details of a sculpture based on the artist and the title of the sculpture. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist': {'type': 'string', 'description': 'The artist who made the sculpture.'}, 'title': {'type': 'string', 'description': 'The title of the sculpture.'}, 'detail': {'type': 'string', 'description': \"The specific detail wanted about the sculpture. Default is 'general information'.\"}}, 'required': ['artist', 'title']}}]\n"}, {"role": "user", "content": "Find the size of the sculpture with title 'David' by Michelangelo."}]]
|
Python
|
simple
|
simple
|
[{"sculpture.get_details": {"artist": ["Michelangelo"], "title": ["David"], "detail": ["size"]}}]
|
simple_265
| false |
[{"name": "sculpture_search", "description": "Find sculptures based on location and a specific time frame.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city where the sculptures are located."}, "time_frame": {"type": "string", "description": "The time frame during which the sculptures were made."}, "material": {"type": "string", "description": "Optional material of the sculptures. Default is 'all'"}}, "required": ["location", "time_frame"]}}]
|
[{"type": "function", "function": {"name": "sculpture_search", "description": "Find sculptures based on location and a specific time frame. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city where the sculptures are located."}, "time_frame": {"type": "string", "description": "The time frame during which the sculptures were made."}, "material": {"type": "string", "description": "Optional material of the sculptures. Default is 'all'"}}, "required": ["location", "time_frame"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sculpture_search', 'description': 'Find sculptures based on location and a specific time frame. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city where the sculptures are located.'}, 'time_frame': {'type': 'string', 'description': 'The time frame during which the sculptures were made.'}, 'material': {'type': 'string', 'description': \"Optional material of the sculptures. Default is 'all'\"}}, 'required': ['location', 'time_frame']}}]\n"}, {"role": "user", "content": "Find me sculptures near Chicago that were made in the 19th century."}]]
|
Python
|
simple
|
simple
|
[{"sculpture_search": {"location": ["Chicago", "Chicago, IL"], "time_frame": ["19th century"], "material": ["", "all"]}}]
|
simple_266
| false |
[{"name": "get_sculpture_value", "description": "Retrieve the current market value of a particular sculpture by a specific artist.", "parameters": {"type": "dict", "properties": {"sculpture": {"type": "string", "description": "The name of the sculpture."}, "artist": {"type": "string", "description": "The name of the artist who created the sculpture."}}, "required": ["sculpture", "artist"]}}]
|
[{"type": "function", "function": {"name": "get_sculpture_value", "description": "Retrieve the current market value of a particular sculpture by a specific artist. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"sculpture": {"type": "string", "description": "The name of the sculpture."}, "artist": {"type": "string", "description": "The name of the artist who created the sculpture."}}, "required": ["sculpture", "artist"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_sculpture_value', 'description': 'Retrieve the current market value of a particular sculpture by a specific artist. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'sculpture': {'type': 'string', 'description': 'The name of the sculpture.'}, 'artist': {'type': 'string', 'description': 'The name of the artist who created the sculpture.'}}, 'required': ['sculpture', 'artist']}}]\n"}, {"role": "user", "content": "What is the value of the sculpture 'The Thinker' by Rodin?"}]]
|
Python
|
simple
|
simple
|
[{"get_sculpture_value": {"sculpture": ["The Thinker"], "artist": ["Rodin"]}}]
|
simple_267
| false |
[{"name": "find_exhibition", "description": "Locate the most popular exhibitions based on criteria like location, time, art form, and user ratings.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city and state where the exhibition is held, e.g., New York City, NY."}, "art_form": {"type": "string", "description": "The form of art the exhibition is displaying e.g., sculpture."}, "month": {"type": "string", "description": "The month of exhibition. Default value will return upcoming events if not specified."}, "user_ratings": {"type": "string", "enum": ["low", "average", "high"], "description": "Select exhibitions with user rating threshold. Default is 'low'"}}, "required": ["location", "art_form"]}}]
|
[{"type": "function", "function": {"name": "find_exhibition", "description": "Locate the most popular exhibitions based on criteria like location, time, art form, and user ratings. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state where the exhibition is held, e.g., New York City, NY."}, "art_form": {"type": "string", "description": "The form of art the exhibition is displaying e.g., sculpture."}, "month": {"type": "string", "description": "The month of exhibition. Default value will return upcoming events if not specified."}, "user_ratings": {"type": "string", "enum": ["low", "average", "high"], "description": "Select exhibitions with user rating threshold. Default is 'low'"}}, "required": ["location", "art_form"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'find_exhibition', 'description': 'Locate the most popular exhibitions based on criteria like location, time, art form, and user ratings. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city and state where the exhibition is held, e.g., New York City, NY.'}, 'art_form': {'type': 'string', 'description': 'The form of art the exhibition is displaying e.g., sculpture.'}, 'month': {'type': 'string', 'description': 'The month of exhibition. Default value will return upcoming events if not specified.'}, 'user_ratings': {'type': 'string', 'enum': ['low', 'average', 'high'], 'description': \"Select exhibitions with user rating threshold. Default is 'low'\"}}, 'required': ['location', 'art_form']}}]\n"}, {"role": "user", "content": "Find the top rated modern sculpture exhibition happening in New York in the upcoming month."}]]
|
Python
|
simple
|
simple
|
[{"find_exhibition": {"location": ["New York City, NY"], "art_form": ["sculpture", "modern sculpture"], "month": [""], "user_ratings": ["high"]}}]
|
simple_268
| false |
[{"name": "sculpture_locator.find_by_artist", "description": "Locate the sculptures of specific artist by material and location", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "Name of the Artist of the sculpture"}, "material": {"type": "string", "description": "Material of the sculpture."}, "location": {"type": "string", "description": "The location where you want to find the sculpture. Default is 'all' if not specified."}}, "required": ["artist", "material"]}}]
|
[{"type": "function", "function": {"name": "sculpture_locator_find_by_artist", "description": "Locate the sculptures of specific artist by material and location Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist": {"type": "string", "description": "Name of the Artist of the sculpture"}, "material": {"type": "string", "description": "Material of the sculpture."}, "location": {"type": "string", "description": "The location where you want to find the sculpture. Default is 'all' if not specified."}}, "required": ["artist", "material"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sculpture_locator.find_by_artist', 'description': 'Locate the sculptures of specific artist by material and location Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist': {'type': 'string', 'description': 'Name of the Artist of the sculpture'}, 'material': {'type': 'string', 'description': 'Material of the sculpture.'}, 'location': {'type': 'string', 'description': \"The location where you want to find the sculpture. Default is 'all' if not specified.\"}}, 'required': ['artist', 'material']}}]\n"}, {"role": "user", "content": "Find me the sculptures of Michelangelo with material Marble in Rome, Italy."}]]
|
Python
|
simple
|
simple
|
[{"sculpture_locator.find_by_artist": {"artist": ["Michelangelo"], "material": ["Marble"], "location": ["Rome", "Rome, Italy"]}}]
|
simple_269
| false |
[{"name": "calculate_compound_interest", "description": "Calculates the compound interest of an investment over a given time period.", "parameters": {"type": "dict", "properties": {"principle": {"type": "integer", "description": "The initial amount of the investment."}, "interest_rate": {"type": "float", "description": "The yearly interest rate of the investment."}, "time": {"type": "integer", "description": "The time, in years, the money is invested or borrowed for."}, "compounds_per_year": {"type": "integer", "description": "The number of times the interest is compounded per year. Default is 1 (interest is compounded yearly)."}}, "required": ["principle", "interest_rate", "time"]}}]
|
[{"type": "function", "function": {"name": "calculate_compound_interest", "description": "Calculates the compound interest of an investment over a given time period. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"principle": {"type": "integer", "description": "The initial amount of the investment."}, "interest_rate": {"type": "number", "description": "The yearly interest rate of the investment. This is a float type value.", "format": "float"}, "time": {"type": "integer", "description": "The time, in years, the money is invested or borrowed for."}, "compounds_per_year": {"type": "integer", "description": "The number of times the interest is compounded per year. Default is 1 (interest is compounded yearly)."}}, "required": ["principle", "interest_rate", "time"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_compound_interest', 'description': 'Calculates the compound interest of an investment over a given time period. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'principle': {'type': 'integer', 'description': 'The initial amount of the investment.'}, 'interest_rate': {'type': 'float', 'description': 'The yearly interest rate of the investment.'}, 'time': {'type': 'integer', 'description': 'The time, in years, the money is invested or borrowed for.'}, 'compounds_per_year': {'type': 'integer', 'description': 'The number of times the interest is compounded per year. Default is 1 (interest is compounded yearly).'}}, 'required': ['principle', 'interest_rate', 'time']}}]\n"}, {"role": "user", "content": "Calculate the compound interest of an investment of $10,000 at an interest rate of 5% compounded yearly for 10 years."}]]
|
Python
|
simple
|
simple
|
[{"calculate_compound_interest": {"principle": [10000], "interest_rate": [0.05], "time": [10], "compounds_per_year": [1, ""]}}]
|
simple_270
| false |
[{"name": "building.get_dimensions", "description": "Retrieve the dimensions of a specific building based on its name.", "parameters": {"type": "dict", "properties": {"building_name": {"type": "string", "description": "The name of the building."}, "unit": {"type": "string", "description": "The unit in which you want the dimensions. Default is meter.", "enum": ["meter", "feet"]}}, "required": ["building_name", "unit"]}}]
|
[{"type": "function", "function": {"name": "building_get_dimensions", "description": "Retrieve the dimensions of a specific building based on its name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"building_name": {"type": "string", "description": "The name of the building."}, "unit": {"type": "string", "description": "The unit in which you want the dimensions. Default is meter.", "enum": ["meter", "feet"]}}, "required": ["building_name", "unit"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'building.get_dimensions', 'description': 'Retrieve the dimensions of a specific building based on its name. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'building_name': {'type': 'string', 'description': 'The name of the building.'}, 'unit': {'type': 'string', 'description': 'The unit in which you want the dimensions. Default is meter.', 'enum': ['meter', 'feet']}}, 'required': ['building_name', 'unit']}}]\n"}, {"role": "user", "content": "Can you give me the height and width of Empire State building in feet?"}]]
|
Python
|
simple
|
simple
|
[{"building.get_dimensions": {"building_name": ["Empire State Building", "Empire State"], "unit": ["feet"]}}]
|
simple_271
| false |
[{"name": "analyze_structure", "description": "Analyze a structure of a building based on its Id and floor numbers.", "parameters": {"type": "dict", "properties": {"building_id": {"type": "string", "description": "The unique identification number of the building."}, "floors": {"type": "array", "items": {"type": "integer"}, "description": "Floor numbers to be analyzed."}, "mode": {"type": "string", "description": "Mode of analysis, e.g. 'static' or 'dynamic'. Default is 'static'."}}, "required": ["building_id", "floors"]}}]
|
[{"type": "function", "function": {"name": "analyze_structure", "description": "Analyze a structure of a building based on its Id and floor numbers. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"building_id": {"type": "string", "description": "The unique identification number of the building."}, "floors": {"type": "array", "items": {"type": "integer"}, "description": "Floor numbers to be analyzed."}, "mode": {"type": "string", "description": "Mode of analysis, e.g. 'static' or 'dynamic'. Default is 'static'."}}, "required": ["building_id", "floors"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'analyze_structure', 'description': 'Analyze a structure of a building based on its Id and floor numbers. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'building_id': {'type': 'string', 'description': 'The unique identification number of the building.'}, 'floors': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'Floor numbers to be analyzed.'}, 'mode': {'type': 'string', 'description': \"Mode of analysis, e.g. 'static' or 'dynamic'. Default is 'static'.\"}}, 'required': ['building_id', 'floors']}}]\n"}, {"role": "user", "content": "What is the structural dynamic analysis of the building with building Id B1004 for 2nd, 3rd and 4th floors?"}]]
|
Python
|
simple
|
simple
|
[{"analyze_structure": {"building_id": ["B1004"], "floors": [[2, 3, 4]], "mode": ["dynamic"]}}]
|
simple_272
| false |
[{"name": "calculate_circle_dimensions", "description": "Calculate the area and circumference of a circle based on the radius.", "parameters": {"type": "dict", "properties": {"radius": {"type": "integer", "description": "The radius of the circle."}}, "required": ["radius"]}}]
|
[{"type": "function", "function": {"name": "calculate_circle_dimensions", "description": "Calculate the area and circumference of a circle based on the radius. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"radius": {"type": "integer", "description": "The radius of the circle."}}, "required": ["radius"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_circle_dimensions', 'description': 'Calculate the area and circumference of a circle based on the radius. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'radius': {'type': 'integer', 'description': 'The radius of the circle.'}}, 'required': ['radius']}}]\n"}, {"role": "user", "content": "Calculate the area and circumference of a circle with a radius of 5 units."}]]
|
Python
|
simple
|
simple
|
[{"calculate_circle_dimensions": {"radius": [5]}}]
|
simple_273
| false |
[{"name": "museum.get_hours", "description": "Retrieve the open hours for a museum based on its name and location.", "parameters": {"type": "dict", "properties": {"name": {"type": "string", "description": "The name of the museum."}, "location": {"type": "string", "description": "The city where the museum is located."}, "day": {"type": "string", "description": "Optional: Day of the week for specific open hours. Default 'Monday'."}}, "required": ["name", "location"]}}]
|
[{"type": "function", "function": {"name": "museum_get_hours", "description": "Retrieve the open hours for a museum based on its name and location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"name": {"type": "string", "description": "The name of the museum."}, "location": {"type": "string", "description": "The city where the museum is located."}, "day": {"type": "string", "description": "Optional: Day of the week for specific open hours. Default 'Monday'."}}, "required": ["name", "location"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'museum.get_hours', 'description': 'Retrieve the open hours for a museum based on its name and location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'name': {'type': 'string', 'description': 'The name of the museum.'}, 'location': {'type': 'string', 'description': 'The city where the museum is located.'}, 'day': {'type': 'string', 'description': \"Optional: Day of the week for specific open hours. Default 'Monday'.\"}}, 'required': ['name', 'location']}}]\n"}, {"role": "user", "content": "Find out the open hours for the Louvre Museum in Paris."}]]
|
Python
|
simple
|
simple
|
[{"museum.get_hours": {"name": ["Louvre Museum"], "location": ["Paris", "Paris, France"], "day": ["", "Monday"]}}]
|
simple_274
| false |
[{"name": "museum_info", "description": "Retrieve information about the opening hours of a museum based on its name.", "parameters": {"type": "dict", "properties": {"museum_name": {"type": "string", "description": "The name of the museum."}, "info_type": {"type": "string", "description": "The type of information needed about the museum.", "default": "opening_hours"}}, "required": ["museum_name"]}}]
|
[{"type": "function", "function": {"name": "museum_info", "description": "Retrieve information about the opening hours of a museum based on its name. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"museum_name": {"type": "string", "description": "The name of the museum."}, "info_type": {"type": "string", "description": "The type of information needed about the museum.", "default": "opening_hours"}}, "required": ["museum_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'museum_info', 'description': 'Retrieve information about the opening hours of a museum based on its name. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'museum_name': {'type': 'string', 'description': 'The name of the museum.'}, 'info_type': {'type': 'string', 'description': 'The type of information needed about the museum.', 'default': 'opening_hours'}}, 'required': ['museum_name']}}]\n"}, {"role": "user", "content": "Find information about the opening hours of the Metropolitan Museum of Art."}]]
|
Python
|
simple
|
simple
|
[{"museum_info": {"museum_name": ["Metropolitan Museum of Art", "The Metropolitan Museum of Art", "Met Museum"], "info_type": ["opening_hours", ""]}}]
|
simple_275
| false |
[{"name": "metropolitan_museum.get_top_artworks", "description": "Fetches the list of popular artworks at the Metropolitan Museum of Art. Results can be sorted based on popularity.", "parameters": {"type": "dict", "properties": {"number": {"type": "integer", "description": "The number of artworks to fetch"}, "sort_by": {"type": "string", "description": "The criteria to sort the results on. Default is 'popularity'.", "enum": ["popularity", "chronological", "alphabetical"]}}, "required": ["number"]}}]
|
[{"type": "function", "function": {"name": "metropolitan_museum_get_top_artworks", "description": "Fetches the list of popular artworks at the Metropolitan Museum of Art. Results can be sorted based on popularity. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"number": {"type": "integer", "description": "The number of artworks to fetch"}, "sort_by": {"type": "string", "description": "The criteria to sort the results on. Default is 'popularity'.", "enum": ["popularity", "chronological", "alphabetical"]}}, "required": ["number"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'metropolitan_museum.get_top_artworks', 'description': 'Fetches the list of popular artworks at the Metropolitan Museum of Art. Results can be sorted based on popularity. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'number': {'type': 'integer', 'description': 'The number of artworks to fetch'}, 'sort_by': {'type': 'string', 'description': \"The criteria to sort the results on. Default is 'popularity'.\", 'enum': ['popularity', 'chronological', 'alphabetical']}}, 'required': ['number']}}]\n"}, {"role": "user", "content": "Get the list of top 5 popular artworks at the Metropolitan Museum of Art. Please sort by popularity."}]]
|
Python
|
simple
|
simple
|
[{"metropolitan_museum.get_top_artworks": {"number": [5], "sort_by": ["popularity", ""]}}]
|
simple_276
| false |
[{"name": "museum_working_hours.get", "description": "Get the working hours of a museum in a specific location.", "parameters": {"type": "dict", "properties": {"museum": {"type": "string", "description": "The name of the museum."}, "location": {"type": "string", "description": "The location of the museum."}, "day": {"type": "string", "description": "Specific day of the week. Default is 'Monday'"}}, "required": ["museum", "location"]}}]
|
[{"type": "function", "function": {"name": "museum_working_hours_get", "description": "Get the working hours of a museum in a specific location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"museum": {"type": "string", "description": "The name of the museum."}, "location": {"type": "string", "description": "The location of the museum."}, "day": {"type": "string", "description": "Specific day of the week. Default is 'Monday'"}}, "required": ["museum", "location"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'museum_working_hours.get', 'description': 'Get the working hours of a museum in a specific location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'museum': {'type': 'string', 'description': 'The name of the museum.'}, 'location': {'type': 'string', 'description': 'The location of the museum.'}, 'day': {'type': 'string', 'description': \"Specific day of the week. Default is 'Monday'\"}}, 'required': ['museum', 'location']}}]\n"}, {"role": "user", "content": "Get the working hours of Louvre Museum in Paris."}]]
|
Python
|
simple
|
simple
|
[{"museum_working_hours.get": {"museum": ["Louvre Museum", "Louvre"], "location": ["Paris", "Paris, France"], "day": ["", "Monday"]}}]
|
simple_277
| false |
[{"name": "museum_info", "description": "Get information about a museum including its opening hours and ticket prices for a specific date range.", "parameters": {"type": "dict", "properties": {"museum": {"type": "string", "description": "The name of the museum."}, "date": {"type": "string", "description": "The specific date for which information is needed, in the format of YYYY-MM-DD such as '2022-12-01'."}, "information": {"type": "array", "items": {"type": "string", "enum": ["opening_hours", "ticket_price", "address"]}, "description": "The type of information needed from the museum. This is optional and defaults to 'all' if not specified.", "default": "all"}}, "required": ["museum", "date"]}}]
|
[{"type": "function", "function": {"name": "museum_info", "description": "Get information about a museum including its opening hours and ticket prices for a specific date range. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"museum": {"type": "string", "description": "The name of the museum."}, "date": {"type": "string", "description": "The specific date for which information is needed, in the format of YYYY-MM-DD such as '2022-12-01'."}, "information": {"type": "array", "items": {"type": "string", "enum": ["opening_hours", "ticket_price", "address"]}, "description": "The type of information needed from the museum. This is optional and defaults to 'all' if not specified.", "default": "all"}}, "required": ["museum", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'museum_info', 'description': 'Get information about a museum including its opening hours and ticket prices for a specific date range. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'museum': {'type': 'string', 'description': 'The name of the museum.'}, 'date': {'type': 'string', 'description': \"The specific date for which information is needed, in the format of YYYY-MM-DD such as '2022-12-01'.\"}, 'information': {'type': 'array', 'items': {'type': 'string', 'enum': ['opening_hours', 'ticket_price', 'address']}, 'description': \"The type of information needed from the museum. This is optional and defaults to 'all' if not specified.\", 'default': 'all'}}, 'required': ['museum', 'date']}}]\n"}, {"role": "user", "content": "Find the working hours and ticket price of The British Museum for this weekend, Jun.20,2023."}]]
|
Python
|
simple
|
simple
|
[{"museum_info": {"museum": ["The British Museum"], "date": ["2023-06-20"], "information": [["opening_hours", "ticket_price"], ["ticket_price", "opening_hours"]]}}]
|
simple_278
| false |
[{"name": "get_instrument_details", "description": "Retrieve the average price and ratings of an instrument from a particular manufacturer.", "parameters": {"type": "dict", "properties": {"instrument": {"type": "string", "description": "The name of the instrument."}, "manufacturer": {"type": "string", "description": "The manufacturer of the instrument."}, "features": {"type": "array", "items": {"type": "string", "enum": ["price", "rating"]}, "description": "The features to retrieve about the instrument. Default is 'price'"}}, "required": ["instrument", "manufacturer"]}}]
|
[{"type": "function", "function": {"name": "get_instrument_details", "description": "Retrieve the average price and ratings of an instrument from a particular manufacturer. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"instrument": {"type": "string", "description": "The name of the instrument."}, "manufacturer": {"type": "string", "description": "The manufacturer of the instrument."}, "features": {"type": "array", "items": {"type": "string", "enum": ["price", "rating"]}, "description": "The features to retrieve about the instrument. Default is 'price'"}}, "required": ["instrument", "manufacturer"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_instrument_details', 'description': 'Retrieve the average price and ratings of an instrument from a particular manufacturer. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'instrument': {'type': 'string', 'description': 'The name of the instrument.'}, 'manufacturer': {'type': 'string', 'description': 'The manufacturer of the instrument.'}, 'features': {'type': 'array', 'items': {'type': 'string', 'enum': ['price', 'rating']}, 'description': \"The features to retrieve about the instrument. Default is 'price'\"}}, 'required': ['instrument', 'manufacturer']}}]\n"}, {"role": "user", "content": "Find me the average price and ratings of piano from Yamaha."}]]
|
Python
|
simple
|
simple
|
[{"get_instrument_details": {"instrument": ["piano"], "manufacturer": ["Yamaha"], "features": [["price", "rating"]]}}]
|
simple_279
| false |
[{"name": "instrument_price.get", "description": "Retrieve the current retail price of a specific musical instrument.", "parameters": {"type": "dict", "properties": {"brand": {"type": "string", "description": "The brand of the instrument."}, "model": {"type": "string", "description": "The specific model of the instrument."}, "finish": {"type": "string", "description": "The color or type of finish on the instrument."}}, "required": ["brand", "model", "finish"]}}]
|
[{"type": "function", "function": {"name": "instrument_price_get", "description": "Retrieve the current retail price of a specific musical instrument. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"brand": {"type": "string", "description": "The brand of the instrument."}, "model": {"type": "string", "description": "The specific model of the instrument."}, "finish": {"type": "string", "description": "The color or type of finish on the instrument."}}, "required": ["brand", "model", "finish"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'instrument_price.get', 'description': 'Retrieve the current retail price of a specific musical instrument. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'brand': {'type': 'string', 'description': 'The brand of the instrument.'}, 'model': {'type': 'string', 'description': 'The specific model of the instrument.'}, 'finish': {'type': 'string', 'description': 'The color or type of finish on the instrument.'}}, 'required': ['brand', 'model', 'finish']}}]\n"}, {"role": "user", "content": "What's the retail price of a Fender American Professional II Stratocaster in Rosewood Finish?"}]]
|
Python
|
simple
|
simple
|
[{"instrument_price.get": {"brand": ["Fender"], "model": ["American Professional II Stratocaster"], "finish": ["Rosewood"]}}]
|
simple_280
| false |
[{"name": "find_instrument", "description": "Search for a musical instrument within specified budget and of specific type.", "parameters": {"type": "dict", "properties": {"budget": {"type": "integer", "description": "Your budget for the instrument."}, "type": {"type": "string", "description": "Type of the instrument"}, "make": {"type": "string", "description": "Maker of the instrument. Default to not use if not specified."}}, "required": ["budget", "type"]}}]
|
[{"type": "function", "function": {"name": "find_instrument", "description": "Search for a musical instrument within specified budget and of specific type. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"budget": {"type": "integer", "description": "Your budget for the instrument."}, "type": {"type": "string", "description": "Type of the instrument"}, "make": {"type": "string", "description": "Maker of the instrument. Default to not use if not specified."}}, "required": ["budget", "type"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'find_instrument', 'description': 'Search for a musical instrument within specified budget and of specific type. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'budget': {'type': 'integer', 'description': 'Your budget for the instrument.'}, 'type': {'type': 'string', 'description': 'Type of the instrument'}, 'make': {'type': 'string', 'description': 'Maker of the instrument. Default to not use if not specified.'}}, 'required': ['budget', 'type']}}]\n"}, {"role": "user", "content": "Find an acoustic instrument within my budget of $1000."}]]
|
Python
|
simple
|
simple
|
[{"find_instrument": {"budget": [1000], "type": ["acoustic"], "make": [""]}}]
|
simple_281
| false |
[{"name": "get_instrument_info", "description": "Retrieve the details about a specific musical instrument based on its name, maker, and manufacturing year.", "parameters": {"type": "dict", "properties": {"name": {"type": "string", "description": "The name of the instrument."}, "maker": {"type": "string", "description": "The name of the maker who created the instrument."}, "year": {"type": "integer", "description": "The year the instrument was made."}}, "required": ["name", "maker", "year"]}}]
|
[{"type": "function", "function": {"name": "get_instrument_info", "description": "Retrieve the details about a specific musical instrument based on its name, maker, and manufacturing year. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"name": {"type": "string", "description": "The name of the instrument."}, "maker": {"type": "string", "description": "The name of the maker who created the instrument."}, "year": {"type": "integer", "description": "The year the instrument was made."}}, "required": ["name", "maker", "year"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_instrument_info', 'description': 'Retrieve the details about a specific musical instrument based on its name, maker, and manufacturing year. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'name': {'type': 'string', 'description': 'The name of the instrument.'}, 'maker': {'type': 'string', 'description': 'The name of the maker who created the instrument.'}, 'year': {'type': 'integer', 'description': 'The year the instrument was made.'}}, 'required': ['name', 'maker', 'year']}}]\n"}, {"role": "user", "content": "Find the details about the musical instrument 'Violin' from 'Stradivarius' maker, made in the year 1721."}]]
|
Python
|
simple
|
simple
|
[{"get_instrument_info": {"name": ["Violin"], "maker": ["Stradivarius"], "year": [1721]}}]
|
simple_282
| false |
[{"name": "find_flute", "description": "Locate a flute for sale based on specific requirements.", "parameters": {"type": "dict", "properties": {"brand": {"type": "string", "description": "The brand of the flute. Example, 'Yamaha'"}, "specs": {"type": "array", "items": {"type": "string", "enum": ["open hole", "C foot", "silver headjoint"]}, "description": "The specifications of the flute desired."}}, "required": ["brand", "specs"]}}]
|
[{"type": "function", "function": {"name": "find_flute", "description": "Locate a flute for sale based on specific requirements. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"brand": {"type": "string", "description": "The brand of the flute. Example, 'Yamaha'"}, "specs": {"type": "array", "items": {"type": "string", "enum": ["open hole", "C foot", "silver headjoint"]}, "description": "The specifications of the flute desired."}}, "required": ["brand", "specs"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'find_flute', 'description': 'Locate a flute for sale based on specific requirements. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'brand': {'type': 'string', 'description': \"The brand of the flute. Example, 'Yamaha'\"}, 'specs': {'type': 'array', 'items': {'type': 'string', 'enum': ['open hole', 'C foot', 'silver headjoint']}, 'description': 'The specifications of the flute desired.'}}, 'required': ['brand', 'specs']}}]\n"}, {"role": "user", "content": "Find a Yamaha flute with the specifications of open hole, C foot, and silver headjoint available for sale."}]]
|
Python
|
simple
|
simple
|
[{"find_flute": {"brand": ["Yamaha"], "specs": [["open hole", "C foot", "silver headjoint"]]}}]
|
simple_283
| false |
[{"name": "guitar_price.find", "description": "Retrieve the price of a specific used guitar model based on its condition and location.", "parameters": {"type": "dict", "properties": {"model": {"type": "string", "description": "The model of the guitar."}, "condition": {"type": "string", "enum": ["Poor", "Good", "Excellent"], "description": "The condition of the guitar."}, "location": {"type": "string", "description": "The location where the guitar is being sold."}}, "required": ["model", "condition", "location"]}}]
|
[{"type": "function", "function": {"name": "guitar_price_find", "description": "Retrieve the price of a specific used guitar model based on its condition and location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"model": {"type": "string", "description": "The model of the guitar."}, "condition": {"type": "string", "enum": ["Poor", "Good", "Excellent"], "description": "The condition of the guitar."}, "location": {"type": "string", "description": "The location where the guitar is being sold."}}, "required": ["model", "condition", "location"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'guitar_price.find', 'description': 'Retrieve the price of a specific used guitar model based on its condition and location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'model': {'type': 'string', 'description': 'The model of the guitar.'}, 'condition': {'type': 'string', 'enum': ['Poor', 'Good', 'Excellent'], 'description': 'The condition of the guitar.'}, 'location': {'type': 'string', 'description': 'The location where the guitar is being sold.'}}, 'required': ['model', 'condition', 'location']}}]\n"}, {"role": "user", "content": "Find the price of a used Gibson Les Paul guitar in excellent condition in the Chicago area."}]]
|
Python
|
simple
|
simple
|
[{"guitar_price.find": {"model": ["Gibson Les Paul"], "condition": ["Excellent"], "location": ["Chicago", "Chicago, IL", "Chicago, Illinois"]}}]
|
simple_284
| false |
[{"name": "concert_info.get", "description": "Retrieve information about concerts based on specific genre, location and date.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city where the concert will take place."}, "date": {"type": "string", "description": "Time frame to get the concert for."}, "genre": {"type": "string", "description": "Genre of the concert.", "enum": ["Pop", "Rock", "Country", "Classical", "Electronic", "Hip-Hop"]}}, "required": ["location", "date", "genre"]}}]
|
[{"type": "function", "function": {"name": "concert_info_get", "description": "Retrieve information about concerts based on specific genre, location and date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city where the concert will take place."}, "date": {"type": "string", "description": "Time frame to get the concert for."}, "genre": {"type": "string", "description": "Genre of the concert.", "enum": ["Pop", "Rock", "Country", "Classical", "Electronic", "Hip-Hop"]}}, "required": ["location", "date", "genre"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert_info.get', 'description': 'Retrieve information about concerts based on specific genre, location and date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city where the concert will take place.'}, 'date': {'type': 'string', 'description': 'Time frame to get the concert for.'}, 'genre': {'type': 'string', 'description': 'Genre of the concert.', 'enum': ['Pop', 'Rock', 'Country', 'Classical', 'Electronic', 'Hip-Hop']}}, 'required': ['location', 'date', 'genre']}}]\n"}, {"role": "user", "content": "Get information about the pop concerts in New York for next month."}]]
|
Python
|
simple
|
simple
|
[{"concert_info.get": {"location": ["New York City, NY", "New York"], "date": ["next month", "2023-06-01", "06/01/2023", "Jun.1,2023", "June 2023"], "genre": ["Pop"]}}]
|
simple_285
| false |
[{"name": "find_concert", "description": "Locate a concert in a specified location within a certain budget.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city where you are looking for a concert. In the format City, State."}, "price": {"type": "integer", "description": "Maximum ticket price."}, "genre": {"type": "string", "description": "Music genre of the concert. Default to 'Jazz'. ", "enum": ["Rock", "Pop", "Country", "Jazz", "Classical"]}}, "required": ["location", "price"]}}]
|
[{"type": "function", "function": {"name": "find_concert", "description": "Locate a concert in a specified location within a certain budget. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city where you are looking for a concert. In the format City, State."}, "price": {"type": "integer", "description": "Maximum ticket price."}, "genre": {"type": "string", "description": "Music genre of the concert. Default to 'Jazz'. ", "enum": ["Rock", "Pop", "Country", "Jazz", "Classical"]}}, "required": ["location", "price"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'find_concert', 'description': 'Locate a concert in a specified location within a certain budget. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city where you are looking for a concert. In the format City, State.'}, 'price': {'type': 'integer', 'description': 'Maximum ticket price.'}, 'genre': {'type': 'string', 'description': \"Music genre of the concert. Default to 'Jazz'. \", 'enum': ['Rock', 'Pop', 'Country', 'Jazz', 'Classical']}}, 'required': ['location', 'price']}}]\n"}, {"role": "user", "content": "Find me a Rock concert in Chicago with ticket availability under $100."}]]
|
Python
|
simple
|
simple
|
[{"find_concert": {"location": ["Chicago, Illinois", "Chicago, IL"], "price": [100], "genre": ["Rock"]}}]
|
simple_286
| false |
[{"name": "concert.get_details", "description": "Fetch the details for a particular concert based on the artist and location.", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "Name of the artist/band who's performing."}, "location": {"type": "string", "description": "City where the concert is taking place."}, "date": {"type": "string", "description": "Date of the concert in 'mm-yyyy' format. Default is the current month if not specified."}}, "required": ["artist", "location"]}}]
|
[{"type": "function", "function": {"name": "concert_get_details", "description": "Fetch the details for a particular concert based on the artist and location. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist": {"type": "string", "description": "Name of the artist/band who's performing."}, "location": {"type": "string", "description": "City where the concert is taking place."}, "date": {"type": "string", "description": "Date of the concert in 'mm-yyyy' format. Default is the current month if not specified."}}, "required": ["artist", "location"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert.get_details', 'description': 'Fetch the details for a particular concert based on the artist and location. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist': {'type': 'string', 'description': \"Name of the artist/band who's performing.\"}, 'location': {'type': 'string', 'description': 'City where the concert is taking place.'}, 'date': {'type': 'string', 'description': \"Date of the concert in 'mm-yyyy' format. Default is the current month if not specified.\"}}, 'required': ['artist', 'location']}}]\n"}, {"role": "user", "content": "Get concert details for the artist Beyonce performing in San Diego next month (April 2022)."}]]
|
Python
|
simple
|
simple
|
[{"concert.get_details": {"artist": ["Beyonce"], "location": ["San Diego", "San Diego, California", "CA"], "date": ["04-2022", "April 2022"]}}]
|
simple_287
| false |
[{"name": "concert.search", "description": "Locate a concert based on specific criteria like genre, location, and date.", "parameters": {"type": "dict", "properties": {"genre": {"type": "string", "description": "Genre of the concert."}, "location": {"type": "string", "description": "City of the concert."}, "date": {"type": "string", "description": "Date of the concert, e.g. this weekend, today, tomorrow.", "enum": ["this weekend", "next weekend", "this month", "next month", "today", "tomorrow", "the day after"]}, "price_range": {"type": "string", "enum": ["free", "cheap", "moderate", "expensive"], "description": "Expected price range of the concert tickets. Default is 'free'."}}, "required": ["genre", "location", "date"]}}]
|
[{"type": "function", "function": {"name": "concert_search", "description": "Locate a concert based on specific criteria like genre, location, and date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"genre": {"type": "string", "description": "Genre of the concert."}, "location": {"type": "string", "description": "City of the concert."}, "date": {"type": "string", "description": "Date of the concert, e.g. this weekend, today, tomorrow.", "enum": ["this weekend", "next weekend", "this month", "next month", "today", "tomorrow", "the day after"]}, "price_range": {"type": "string", "enum": ["free", "cheap", "moderate", "expensive"], "description": "Expected price range of the concert tickets. Default is 'free'."}}, "required": ["genre", "location", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert.search', 'description': 'Locate a concert based on specific criteria like genre, location, and date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'genre': {'type': 'string', 'description': 'Genre of the concert.'}, 'location': {'type': 'string', 'description': 'City of the concert.'}, 'date': {'type': 'string', 'description': 'Date of the concert, e.g. this weekend, today, tomorrow.', 'enum': ['this weekend', 'next weekend', 'this month', 'next month', 'today', 'tomorrow', 'the day after']}, 'price_range': {'type': 'string', 'enum': ['free', 'cheap', 'moderate', 'expensive'], 'description': \"Expected price range of the concert tickets. Default is 'free'.\"}}, 'required': ['genre', 'location', 'date']}}]\n"}, {"role": "user", "content": "Find me a classical concert this weekend in Los Angeles with cheap tickets."}]]
|
Python
|
simple
|
simple
|
[{"concert.search": {"genre": ["classical"], "location": ["Los Angeles", "LA"], "date": ["this weekend"], "price_range": ["cheap"]}}]
|
simple_288
| false |
[{"name": "concert_booking.book_ticket", "description": "Book concert tickets for a specific artist in a specified city.", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "The artist you want to book tickets for."}, "city": {"type": "string", "description": "The city where the concert is."}, "num_tickets": {"type": "integer", "description": "Number of tickets required. Default is 1."}}, "required": ["artist", "city"]}}]
|
[{"type": "function", "function": {"name": "concert_booking_book_ticket", "description": "Book concert tickets for a specific artist in a specified city. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist": {"type": "string", "description": "The artist you want to book tickets for."}, "city": {"type": "string", "description": "The city where the concert is."}, "num_tickets": {"type": "integer", "description": "Number of tickets required. Default is 1."}}, "required": ["artist", "city"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert_booking.book_ticket', 'description': 'Book concert tickets for a specific artist in a specified city. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist': {'type': 'string', 'description': 'The artist you want to book tickets for.'}, 'city': {'type': 'string', 'description': 'The city where the concert is.'}, 'num_tickets': {'type': 'integer', 'description': 'Number of tickets required. Default is 1.'}}, 'required': ['artist', 'city']}}]\n"}, {"role": "user", "content": "Get me two tickets for next Eminem concert in New York City."}]]
|
Python
|
simple
|
simple
|
[{"concert_booking.book_ticket": {"artist": ["Eminem"], "city": ["New York City", "New York City, NY", "NYC"], "num_tickets": [2]}}]
|
simple_289
| false |
[{"name": "concert.find_nearby", "description": "Locate nearby concerts based on specific criteria like genre.", "parameters": {"type": "dict", "properties": {"location": {"type": "string", "description": "The city and state, e.g. Seattle, WA"}, "genre": {"type": "string", "description": "Genre of music to be played at the concert."}}, "required": ["location", "genre"]}}]
|
[{"type": "function", "function": {"name": "concert_find_nearby", "description": "Locate nearby concerts based on specific criteria like genre. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. Seattle, WA"}, "genre": {"type": "string", "description": "Genre of music to be played at the concert."}}, "required": ["location", "genre"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert.find_nearby', 'description': 'Locate nearby concerts based on specific criteria like genre. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'location': {'type': 'string', 'description': 'The city and state, e.g. Seattle, WA'}, 'genre': {'type': 'string', 'description': 'Genre of music to be played at the concert.'}}, 'required': ['location', 'genre']}}]\n"}, {"role": "user", "content": "Find concerts near me in Seattle that plays jazz music."}]]
|
Python
|
simple
|
simple
|
[{"concert.find_nearby": {"location": ["Seattle", "Seattle, WA"], "genre": ["jazz", "Jazz"]}}]
|
simple_290
| false |
[{"name": "concert.find_details", "description": "Finds details of a concert event.", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "Name of the artist performing."}, "month": {"type": "string", "description": "Month in which the concert is happening."}, "year": {"type": "integer", "description": "Year of the concert.", "default": 2022}}, "required": ["artist", "month"]}}]
|
[{"type": "function", "function": {"name": "concert_find_details", "description": "Finds details of a concert event. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"artist": {"type": "string", "description": "Name of the artist performing."}, "month": {"type": "string", "description": "Month in which the concert is happening."}, "year": {"type": "integer", "description": "Year of the concert.", "default": 2022}}, "required": ["artist", "month"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'concert.find_details', 'description': 'Finds details of a concert event. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'artist': {'type': 'string', 'description': 'Name of the artist performing.'}, 'month': {'type': 'string', 'description': 'Month in which the concert is happening.'}, 'year': {'type': 'integer', 'description': 'Year of the concert.', 'default': 2022}}, 'required': ['artist', 'month']}}]\n"}, {"role": "user", "content": "What's the timing and location for The Weeknd's concert happening in December?"}]]
|
Python
|
simple
|
simple
|
[{"concert.find_details": {"artist": ["The Weeknd"], "month": ["December"], "year": ["", 2022]}}]
|
simple_291
| false |
[{"name": "music_generator.generate_melody", "description": "Generate a melody based on certain musical parameters.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The key of the melody. E.g., 'C' for C major."}, "start_note": {"type": "string", "description": "The first note of the melody, specified in scientific pitch notation. E.g., 'C4'."}, "length": {"type": "integer", "description": "The number of measures in the melody."}, "tempo": {"type": "integer", "description": "The tempo of the melody, in beats per minute. Optional parameter. If not specified, defaults to 120."}}, "required": ["key", "start_note", "length"]}}]
|
[{"type": "function", "function": {"name": "music_generator_generate_melody", "description": "Generate a melody based on certain musical parameters. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The key of the melody. E.g., 'C' for C major."}, "start_note": {"type": "string", "description": "The first note of the melody, specified in scientific pitch notation. E.g., 'C4'."}, "length": {"type": "integer", "description": "The number of measures in the melody."}, "tempo": {"type": "integer", "description": "The tempo of the melody, in beats per minute. Optional parameter. If not specified, defaults to 120."}}, "required": ["key", "start_note", "length"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music_generator.generate_melody', 'description': 'Generate a melody based on certain musical parameters. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': \"The key of the melody. E.g., 'C' for C major.\"}, 'start_note': {'type': 'string', 'description': \"The first note of the melody, specified in scientific pitch notation. E.g., 'C4'.\"}, 'length': {'type': 'integer', 'description': 'The number of measures in the melody.'}, 'tempo': {'type': 'integer', 'description': 'The tempo of the melody, in beats per minute. Optional parameter. If not specified, defaults to 120.'}}, 'required': ['key', 'start_note', 'length']}}]\n"}, {"role": "user", "content": "Generate a melody in C major scale, starting with the note C4, 16 measures long, at 120 beats per minute."}]]
|
Python
|
simple
|
simple
|
[{"music_generator.generate_melody": {"key": ["C"], "start_note": ["C4"], "length": [16], "tempo": [120, ""]}}]
|
simple_292
| false |
[{"name": "compose_melody", "description": "Compose a melody using the specified chord progression for a certain number of measures on specified instrument.", "parameters": {"type": "dict", "properties": {"progression": {"type": "array", "items": {"type": "string"}, "description": "The progression of chords."}, "measures": {"type": "integer", "description": "The number of measures of the melody."}, "instrument": {"type": "string", "description": "The instrument for the composition. Default is 'Piano'."}}, "required": ["progression", "measures"]}}]
|
[{"type": "function", "function": {"name": "compose_melody", "description": "Compose a melody using the specified chord progression for a certain number of measures on specified instrument. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"progression": {"type": "array", "items": {"type": "string"}, "description": "The progression of chords."}, "measures": {"type": "integer", "description": "The number of measures of the melody."}, "instrument": {"type": "string", "description": "The instrument for the composition. Default is 'Piano'."}}, "required": ["progression", "measures"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'compose_melody', 'description': 'Compose a melody using the specified chord progression for a certain number of measures on specified instrument. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'progression': {'type': 'array', 'items': {'type': 'string'}, 'description': 'The progression of chords.'}, 'measures': {'type': 'integer', 'description': 'The number of measures of the melody.'}, 'instrument': {'type': 'string', 'description': \"The instrument for the composition. Default is 'Piano'.\"}}, 'required': ['progression', 'measures']}}]\n"}, {"role": "user", "content": "Compose a simple piano melody with a progression of C, F and G for 4 measures."}]]
|
Python
|
simple
|
simple
|
[{"compose_melody": {"progression": [["C", "F", "G"]], "measures": [4], "instrument": ["Piano", ""]}}]
|
simple_293
| false |
[{"name": "music_composer.create_mix", "description": "Create a mix of a song based on a particular music scale and duration", "parameters": {"type": "dict", "properties": {"scale": {"type": "string", "description": "The musical scale to be used. E.g: C Major, A Minor, etc."}, "note_duration": {"type": "string", "description": "Duration of each note. Options: 'whole', 'half', 'quarter', 'eighth', 'sixteenth'.", "enum": ["whole", "half", "quarter", "eighth", "sixteenth"]}, "track_length": {"type": "integer", "description": "Length of the mix track in seconds."}}, "required": ["scale", "note_duration", "track_length"]}}]
|
[{"type": "function", "function": {"name": "music_composer_create_mix", "description": "Create a mix of a song based on a particular music scale and duration Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"scale": {"type": "string", "description": "The musical scale to be used. E.g: C Major, A Minor, etc."}, "note_duration": {"type": "string", "description": "Duration of each note. Options: 'whole', 'half', 'quarter', 'eighth', 'sixteenth'.", "enum": ["whole", "half", "quarter", "eighth", "sixteenth"]}, "track_length": {"type": "integer", "description": "Length of the mix track in seconds."}}, "required": ["scale", "note_duration", "track_length"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music_composer.create_mix', 'description': 'Create a mix of a song based on a particular music scale and duration Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'scale': {'type': 'string', 'description': 'The musical scale to be used. E.g: C Major, A Minor, etc.'}, 'note_duration': {'type': 'string', 'description': \"Duration of each note. Options: 'whole', 'half', 'quarter', 'eighth', 'sixteenth'.\", 'enum': ['whole', 'half', 'quarter', 'eighth', 'sixteenth']}, 'track_length': {'type': 'integer', 'description': 'Length of the mix track in seconds.'}}, 'required': ['scale', 'note_duration', 'track_length']}}]\n"}, {"role": "user", "content": "Create a mix track using notes of C major scale and duration of each note being quarter of a second with a duration of 3 minutes."}]]
|
Python
|
simple
|
simple
|
[{"music_composer.create_mix": {"scale": ["C Major"], "note_duration": ["quarter"], "track_length": [180]}}]
|
simple_294
| false |
[{"name": "music_generation.create_chord_progression", "description": "Create a chord progression in a specific key and number of chords.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The key for the chord progression."}, "chords": {"type": "integer", "description": "Number of chords in the progression."}, "progression_type": {"type": "string", "description": "The type of the chord progression. Optional parameter. Default is 'major'."}}, "required": ["key", "chords"]}}]
|
[{"type": "function", "function": {"name": "music_generation_create_chord_progression", "description": "Create a chord progression in a specific key and number of chords. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The key for the chord progression."}, "chords": {"type": "integer", "description": "Number of chords in the progression."}, "progression_type": {"type": "string", "description": "The type of the chord progression. Optional parameter. Default is 'major'."}}, "required": ["key", "chords"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music_generation.create_chord_progression', 'description': 'Create a chord progression in a specific key and number of chords. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': 'The key for the chord progression.'}, 'chords': {'type': 'integer', 'description': 'Number of chords in the progression.'}, 'progression_type': {'type': 'string', 'description': \"The type of the chord progression. Optional parameter. Default is 'major'.\"}}, 'required': ['key', 'chords']}}]\n"}, {"role": "user", "content": "Generate a major chord progression in C key with four chords."}]]
|
Python
|
simple
|
simple
|
[{"music_generation.create_chord_progression": {"key": ["C"], "chords": [4], "progression_type": ["major", ""]}}]
|
simple_295
| false |
[{"name": "get_song_lyrics", "description": "Retrieve the lyrics of a song based on the artist's name and song title.", "parameters": {"type": "dict", "properties": {"song_title": {"type": "string", "description": "The title of the song."}, "artist_name": {"type": "string", "description": "The name of the artist who performed the song."}, "lang": {"type": "string", "description": "The language of the lyrics. Default is English.", "enum": ["English", "French", "Spanish", "German", "Italian"]}}, "required": ["song_title", "artist_name"]}}]
|
[{"type": "function", "function": {"name": "get_song_lyrics", "description": "Retrieve the lyrics of a song based on the artist's name and song title. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"song_title": {"type": "string", "description": "The title of the song."}, "artist_name": {"type": "string", "description": "The name of the artist who performed the song."}, "lang": {"type": "string", "description": "The language of the lyrics. Default is English.", "enum": ["English", "French", "Spanish", "German", "Italian"]}}, "required": ["song_title", "artist_name"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_song_lyrics', 'description': \"Retrieve the lyrics of a song based on the artist's name and song title. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'properties': {'song_title': {'type': 'string', 'description': 'The title of the song.'}, 'artist_name': {'type': 'string', 'description': 'The name of the artist who performed the song.'}, 'lang': {'type': 'string', 'description': 'The language of the lyrics. Default is English.', 'enum': ['English', 'French', 'Spanish', 'German', 'Italian']}}, 'required': ['song_title', 'artist_name']}}]\n"}, {"role": "user", "content": "Find the lyrics to the song 'Bohemian Rhapsody' by Queen."}]]
|
Python
|
simple
|
simple
|
[{"get_song_lyrics": {"song_title": ["Bohemian Rhapsody"], "artist_name": ["Queen"], "lang": ["English", ""]}}]
|
simple_296
| false |
[{"name": "music_generator.generate_scale_progression", "description": "Generate a music scale progression in a specific key with a given tempo and duration.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The key in which to generate the scale progression."}, "tempo": {"type": "integer", "description": "The tempo of the scale progression in BPM."}, "duration": {"type": "integer", "description": "The duration of each note in beats."}, "scale_type": {"type": "string", "default": "major", "description": "The type of scale to generate. Defaults to 'major'."}}, "required": ["key", "tempo", "duration"]}}]
|
[{"type": "function", "function": {"name": "music_generator_generate_scale_progression", "description": "Generate a music scale progression in a specific key with a given tempo and duration. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The key in which to generate the scale progression."}, "tempo": {"type": "integer", "description": "The tempo of the scale progression in BPM."}, "duration": {"type": "integer", "description": "The duration of each note in beats."}, "scale_type": {"type": "string", "default": "major", "description": "The type of scale to generate. Defaults to 'major'."}}, "required": ["key", "tempo", "duration"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music_generator.generate_scale_progression', 'description': 'Generate a music scale progression in a specific key with a given tempo and duration. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': 'The key in which to generate the scale progression.'}, 'tempo': {'type': 'integer', 'description': 'The tempo of the scale progression in BPM.'}, 'duration': {'type': 'integer', 'description': 'The duration of each note in beats.'}, 'scale_type': {'type': 'string', 'default': 'major', 'description': \"The type of scale to generate. Defaults to 'major'.\"}}, 'required': ['key', 'tempo', 'duration']}}]\n"}, {"role": "user", "content": "Generate a major C scale progression with tempo 80 BPM and duration 4 beats."}]]
|
Python
|
simple
|
simple
|
[{"music_generator.generate_scale_progression": {"key": ["C"], "tempo": [80], "duration": [4], "scale_type": ["major", ""]}}]
|
simple_297
| false |
[{"name": "music.theory.chordProgression", "description": "Identifies a potential key signature for the given chord progression.", "parameters": {"type": "dict", "properties": {"progression": {"type": "array", "items": {"type": "string"}, "description": "The chord progression in Roman numerals. Eg: ['I', 'V', 'vi', 'IV']."}, "returnAllPossibleKeys": {"type": "boolean", "description": "Flag indicating if the function should return all possible key signatures that fit the chord progression. If false, the function will return the first valid key it finds. Default is false."}, "assumeMajor": {"type": "boolean", "description": "Assumption if the key signature is Major. If true, the function will assume the key signature to be major and otherwise minor. Default is true."}}, "required": ["progression"]}}]
|
[{"type": "function", "function": {"name": "music_theory_chordProgression", "description": "Identifies a potential key signature for the given chord progression. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"progression": {"type": "array", "items": {"type": "string"}, "description": "The chord progression in Roman numerals. Eg: ['I', 'V', 'vi', 'IV']."}, "returnAllPossibleKeys": {"type": "boolean", "description": "Flag indicating if the function should return all possible key signatures that fit the chord progression. If false, the function will return the first valid key it finds. Default is false."}, "assumeMajor": {"type": "boolean", "description": "Assumption if the key signature is Major. If true, the function will assume the key signature to be major and otherwise minor. Default is true."}}, "required": ["progression"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music.theory.chordProgression', 'description': 'Identifies a potential key signature for the given chord progression. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'progression': {'type': 'array', 'items': {'type': 'string'}, 'description': \"The chord progression in Roman numerals. Eg: ['I', 'V', 'vi', 'IV'].\"}, 'returnAllPossibleKeys': {'type': 'boolean', 'description': 'Flag indicating if the function should return all possible key signatures that fit the chord progression. If false, the function will return the first valid key it finds. Default is false.'}, 'assumeMajor': {'type': 'boolean', 'description': 'Assumption if the key signature is Major. If true, the function will assume the key signature to be major and otherwise minor. Default is true.'}}, 'required': ['progression']}}]\n"}, {"role": "user", "content": "music.theory.chordProgression(progression=['I', 'V', 'vi', 'IV'])"}]]
|
Python
|
simple
|
simple
|
[{"music.theory.chordProgression": {"progression": [["I", "V", "vi", "IV"]], "returnAllPossibleKeys": [true, false, ""], "assumeMajor": [true, false, ""]}}]
|
simple_298
| false |
[{"name": "music_theory.key_signature", "description": "Return the key signature of a major or minor scale.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The root of the scale, e.g., 'C', 'F#', 'Ab'."}, "scale_type": {"type": "string", "enum": ["major", "minor"], "description": "Type of the scale, either 'major' or 'minor'. Default is 'major'."}}, "required": ["key"]}}]
|
[{"type": "function", "function": {"name": "music_theory_key_signature", "description": "Return the key signature of a major or minor scale. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The root of the scale, e.g., 'C', 'F#', 'Ab'."}, "scale_type": {"type": "string", "enum": ["major", "minor"], "description": "Type of the scale, either 'major' or 'minor'. Default is 'major'."}}, "required": ["key"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music_theory.key_signature', 'description': 'Return the key signature of a major or minor scale. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': \"The root of the scale, e.g., 'C', 'F#', 'Ab'.\"}, 'scale_type': {'type': 'string', 'enum': ['major', 'minor'], 'description': \"Type of the scale, either 'major' or 'minor'. Default is 'major'.\"}}, 'required': ['key']}}]\n"}, {"role": "user", "content": "What key signature does C# major have?"}]]
|
Python
|
simple
|
simple
|
[{"music_theory.key_signature": {"key": ["C#"], "scale_type": ["major", ""]}}]
|
simple_299
| false |
[{"name": "musical_scale", "description": "Get the musical scale of a specific key in music theory.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The musical key for which the scale will be found."}, "scale_type": {"type": "string", "default": "major", "description": "The type of musical scale."}}, "required": ["key"]}}]
|
[{"type": "function", "function": {"name": "musical_scale", "description": "Get the musical scale of a specific key in music theory. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The musical key for which the scale will be found."}, "scale_type": {"type": "string", "default": "major", "description": "The type of musical scale."}}, "required": ["key"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'musical_scale', 'description': 'Get the musical scale of a specific key in music theory. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': 'The musical key for which the scale will be found.'}, 'scale_type': {'type': 'string', 'default': 'major', 'description': 'The type of musical scale.'}}, 'required': ['key']}}]\n"}, {"role": "user", "content": "What is the musical scale associated with C sharp major?"}]]
|
Python
|
simple
|
simple
|
[{"musical_scale": {"key": ["C#", "C sharp"], "scale_type": ["major", ""]}}]
|
simple_300
| false |
[{"name": "music.calculate_note_duration", "description": "Calculate the duration between two notes based on their frequencies and harmonic rhythm.", "parameters": {"type": "dict", "properties": {"first_note_frequency": {"type": "integer", "description": "The frequency of the first note in Hz."}, "second_note_frequency": {"type": "integer", "description": "The frequency of the second note in Hz."}, "tempo": {"type": "integer", "description": "The tempo of the music in beats per minute. Defaults to 120 beats per minute."}}, "required": ["first_note_frequency", "second_note_frequency"]}}]
|
[{"type": "function", "function": {"name": "music_calculate_note_duration", "description": "Calculate the duration between two notes based on their frequencies and harmonic rhythm. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"first_note_frequency": {"type": "integer", "description": "The frequency of the first note in Hz."}, "second_note_frequency": {"type": "integer", "description": "The frequency of the second note in Hz."}, "tempo": {"type": "integer", "description": "The tempo of the music in beats per minute. Defaults to 120 beats per minute."}}, "required": ["first_note_frequency", "second_note_frequency"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'music.calculate_note_duration', 'description': 'Calculate the duration between two notes based on their frequencies and harmonic rhythm. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'first_note_frequency': {'type': 'integer', 'description': 'The frequency of the first note in Hz.'}, 'second_note_frequency': {'type': 'integer', 'description': 'The frequency of the second note in Hz.'}, 'tempo': {'type': 'integer', 'description': 'The tempo of the music in beats per minute. Defaults to 120 beats per minute.'}}, 'required': ['first_note_frequency', 'second_note_frequency']}}]\n"}, {"role": "user", "content": "Calculate the duration between two notes of 440Hz and 880Hz frequency based on harmonic rhythm."}]]
|
Python
|
simple
|
simple
|
[{"music.calculate_note_duration": {"first_note_frequency": [440], "second_note_frequency": [880], "tempo": ["", 120]}}]
|
simple_301
| false |
[{"name": "get_third_chord", "description": "Calculate the third major chord in a given key.", "parameters": {"type": "dict", "properties": {"key": {"type": "string", "description": "The key of the scale."}, "type": {"type": "string", "description": "Type of the scale, either major or minor. Default is 'major'."}}, "required": ["key"]}}]
|
[{"type": "function", "function": {"name": "get_third_chord", "description": "Calculate the third major chord in a given key. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"key": {"type": "string", "description": "The key of the scale."}, "type": {"type": "string", "description": "Type of the scale, either major or minor. Default is 'major'."}}, "required": ["key"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'get_third_chord', 'description': 'Calculate the third major chord in a given key. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'key': {'type': 'string', 'description': 'The key of the scale.'}, 'type': {'type': 'string', 'description': \"Type of the scale, either major or minor. Default is 'major'.\"}}, 'required': ['key']}}]\n"}, {"role": "user", "content": "What is the third major chord in C major scale?"}]]
|
Python
|
simple
|
simple
|
[{"get_third_chord": {"key": ["C"], "type": ["major", ""]}}]
|
simple_302
| false |
[{"name": "calculate_batting_average", "description": "Calculate the batting average for a baseball player based on their number of hits and at-bats.", "parameters": {"type": "dict", "properties": {"hits": {"type": "integer", "description": "The number of hits."}, "at_bats": {"type": "integer", "description": "The number of at-bats."}, "decimal_places": {"type": "integer", "description": "The number of decimal places to return in the batting average. Default is 3."}}, "required": ["hits", "at_bats"]}}]
|
[{"type": "function", "function": {"name": "calculate_batting_average", "description": "Calculate the batting average for a baseball player based on their number of hits and at-bats. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"hits": {"type": "integer", "description": "The number of hits."}, "at_bats": {"type": "integer", "description": "The number of at-bats."}, "decimal_places": {"type": "integer", "description": "The number of decimal places to return in the batting average. Default is 3."}}, "required": ["hits", "at_bats"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'calculate_batting_average', 'description': 'Calculate the batting average for a baseball player based on their number of hits and at-bats. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'hits': {'type': 'integer', 'description': 'The number of hits.'}, 'at_bats': {'type': 'integer', 'description': 'The number of at-bats.'}, 'decimal_places': {'type': 'integer', 'description': 'The number of decimal places to return in the batting average. Default is 3.'}}, 'required': ['hits', 'at_bats']}}]\n"}, {"role": "user", "content": "Calculate the batting average for a baseball player who has 180 hits and 600 at-bats. Round to 3 decimals."}]]
|
Python
|
simple
|
simple
|
[{"calculate_batting_average": {"hits": [180], "at_bats": [600], "decimal_places": [3, ""]}}]
|
simple_303
| false |
[{"name": "soccer_stat.get_player_stats", "description": "Retrieve soccer player statistics for a given season.", "parameters": {"type": "dict", "properties": {"player_name": {"type": "string", "description": "Name of the player."}, "season": {"type": "string", "description": "Soccer season, usually specified by two years."}, "league": {"type": "string", "description": "Optional - the soccer league, defaults to all leagues if not specified."}}, "required": ["player_name", "season"]}}]
|
[{"type": "function", "function": {"name": "soccer_stat_get_player_stats", "description": "Retrieve soccer player statistics for a given season. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"player_name": {"type": "string", "description": "Name of the player."}, "season": {"type": "string", "description": "Soccer season, usually specified by two years."}, "league": {"type": "string", "description": "Optional - the soccer league, defaults to all leagues if not specified."}}, "required": ["player_name", "season"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'soccer_stat.get_player_stats', 'description': 'Retrieve soccer player statistics for a given season. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'player_name': {'type': 'string', 'description': 'Name of the player.'}, 'season': {'type': 'string', 'description': 'Soccer season, usually specified by two years.'}, 'league': {'type': 'string', 'description': 'Optional - the soccer league, defaults to all leagues if not specified.'}}, 'required': ['player_name', 'season']}}]\n"}, {"role": "user", "content": "Get the player stats of Cristiano Ronaldo in the 2019-2020 season"}]]
|
Python
|
simple
|
simple
|
[{"soccer_stat.get_player_stats": {"player_name": ["Cristiano Ronaldo"], "season": ["2019-2020"], "league": [""]}}]
|
simple_304
| false |
[{"name": "player_stats.getLastGame", "description": "Get last game statistics for a specific player in basketball", "parameters": {"type": "dict", "properties": {"player_name": {"type": "string", "description": "The name of the basketball player."}, "team": {"type": "string", "description": "The team that player currently plays for."}, "metrics": {"type": "array", "items": {"type": "string", "enum": ["Points", "Rebounds", "Assists", "Blocks"]}, "description": "Specific metrics to retrieve. If no value is specified, all available metrics will be returned by default."}}, "required": ["player_name", "team"]}}]
|
[{"type": "function", "function": {"name": "player_stats_getLastGame", "description": "Get last game statistics for a specific player in basketball Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"player_name": {"type": "string", "description": "The name of the basketball player."}, "team": {"type": "string", "description": "The team that player currently plays for."}, "metrics": {"type": "array", "items": {"type": "string", "enum": ["Points", "Rebounds", "Assists", "Blocks"]}, "description": "Specific metrics to retrieve. If no value is specified, all available metrics will be returned by default."}}, "required": ["player_name", "team"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'player_stats.getLastGame', 'description': 'Get last game statistics for a specific player in basketball Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'player_name': {'type': 'string', 'description': 'The name of the basketball player.'}, 'team': {'type': 'string', 'description': 'The team that player currently plays for.'}, 'metrics': {'type': 'array', 'items': {'type': 'string', 'enum': ['Points', 'Rebounds', 'Assists', 'Blocks']}, 'description': 'Specific metrics to retrieve. If no value is specified, all available metrics will be returned by default.'}}, 'required': ['player_name', 'team']}}]\n"}, {"role": "user", "content": "Get point and rebound stats for player 'LeBron James' from last basketball game"}]]
|
Python
|
simple
|
simple
|
[{"player_stats.getLastGame": {"player_name": ["LeBron James"], "team": ["Los Angeles Lakers", "LAL", "Lakers"], "metrics": [["Points", "Rebounds"]]}}]
|
simple_305
| false |
[{"name": "sports_stats.get_performance", "description": "Compute the performance score of a soccer player given his game stats for a specific tournament in a season.", "parameters": {"type": "dict", "properties": {"player_name": {"type": "string", "description": "Name of the player."}, "tournament": {"type": "string", "description": "Name of the soccer tournament."}, "season": {"type": "string", "description": "Specific season in format 'YYYY-YYYY'."}, "performance_indicator": {"type": "array", "items": {"type": "string", "enum": ["Goals Scored", "Assists Made", "Saves Made", "Cards Received"]}, "description": "Array of performance indicators. Use as much as possible. Default to use all if not specified."}}, "required": ["player_name", "tournament", "season"]}}]
|
[{"type": "function", "function": {"name": "sports_stats_get_performance", "description": "Compute the performance score of a soccer player given his game stats for a specific tournament in a season. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"player_name": {"type": "string", "description": "Name of the player."}, "tournament": {"type": "string", "description": "Name of the soccer tournament."}, "season": {"type": "string", "description": "Specific season in format 'YYYY-YYYY'."}, "performance_indicator": {"type": "array", "items": {"type": "string", "enum": ["Goals Scored", "Assists Made", "Saves Made", "Cards Received"]}, "description": "Array of performance indicators. Use as much as possible. Default to use all if not specified."}}, "required": ["player_name", "tournament", "season"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sports_stats.get_performance', 'description': 'Compute the performance score of a soccer player given his game stats for a specific tournament in a season. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'player_name': {'type': 'string', 'description': 'Name of the player.'}, 'tournament': {'type': 'string', 'description': 'Name of the soccer tournament.'}, 'season': {'type': 'string', 'description': \"Specific season in format 'YYYY-YYYY'.\"}, 'performance_indicator': {'type': 'array', 'items': {'type': 'string', 'enum': ['Goals Scored', 'Assists Made', 'Saves Made', 'Cards Received']}, 'description': 'Array of performance indicators. Use as much as possible. Default to use all if not specified.'}}, 'required': ['player_name', 'tournament', 'season']}}]\n"}, {"role": "user", "content": "Calculate the overall goal and assist of soccer player Messi in La Liga 2020-2021 season"}]]
|
Python
|
simple
|
simple
|
[{"sports_stats.get_performance": {"player_name": ["Messi", "Lionel Messi"], "tournament": ["La Liga"], "season": ["2020-2021"], "performance_indicator": [["Goals Scored", "Assists Made"]]}}]
|
simple_306
| false |
[{"name": "average_batting_score", "description": "Get the average batting score of a cricketer for specified past matches.", "parameters": {"type": "dict", "properties": {"player_name": {"type": "string", "description": "Name of the cricket player."}, "matches": {"type": "integer", "description": "Number of past matches to consider for average calculation."}, "match_format": {"type": "string", "description": "Format of the cricket matches considered (e.g., 'T20', 'ODI', 'Test'). Default is 'T20'."}}, "required": ["player_name", "matches"]}}]
|
[{"type": "function", "function": {"name": "average_batting_score", "description": "Get the average batting score of a cricketer for specified past matches. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"player_name": {"type": "string", "description": "Name of the cricket player."}, "matches": {"type": "integer", "description": "Number of past matches to consider for average calculation."}, "match_format": {"type": "string", "description": "Format of the cricket matches considered (e.g., 'T20', 'ODI', 'Test'). Default is 'T20'."}}, "required": ["player_name", "matches"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'average_batting_score', 'description': 'Get the average batting score of a cricketer for specified past matches. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'player_name': {'type': 'string', 'description': 'Name of the cricket player.'}, 'matches': {'type': 'integer', 'description': 'Number of past matches to consider for average calculation.'}, 'match_format': {'type': 'string', 'description': \"Format of the cricket matches considered (e.g., 'T20', 'ODI', 'Test'). Default is 'T20'.\"}}, 'required': ['player_name', 'matches']}}]\n"}, {"role": "user", "content": "Find average batting score of a cricketer, Virat Kohli for past 10 matches"}]]
|
Python
|
simple
|
simple
|
[{"average_batting_score": {"player_name": ["Virat Kohli"], "matches": [10], "match_format": ["T20", ""]}}]
|
simple_307
| false |
[{"name": "game_result.get_winner", "description": "Get the winner of a specific basketball game.", "parameters": {"type": "dict", "properties": {"teams": {"type": "array", "items": {"type": "string"}, "description": "List of two teams who played the game."}, "date": {"type": "string", "description": "The date of the game, formatted as YYYY-MM-DD."}, "venue": {"type": "string", "optional": true, "description": "Optional: The venue of the game. Default is 'home'."}}, "required": ["teams", "date"]}}]
|
[{"type": "function", "function": {"name": "game_result_get_winner", "description": "Get the winner of a specific basketball game. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"teams": {"type": "array", "items": {"type": "string"}, "description": "List of two teams who played the game."}, "date": {"type": "string", "description": "The date of the game, formatted as YYYY-MM-DD."}, "venue": {"type": "string", "optional": true, "description": "Optional: The venue of the game. Default is 'home'."}}, "required": ["teams", "date"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'game_result.get_winner', 'description': 'Get the winner of a specific basketball game. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'teams': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of two teams who played the game.'}, 'date': {'type': 'string', 'description': 'The date of the game, formatted as YYYY-MM-DD.'}, 'venue': {'type': 'string', 'optional': True, 'description': \"Optional: The venue of the game. Default is 'home'.\"}}, 'required': ['teams', 'date']}}]\n"}, {"role": "user", "content": "Who won the basketball game between Lakers and Clippers on Jan 28, 2021?"}]]
|
Python
|
simple
|
simple
|
[{"game_result.get_winner": {"teams": [["Lakers", "Clippers"], ["Clippers", "Lakers"]], "date": ["2021-01-28", "01/28/2021", "Jan.28,2021"], "venue": ["", true]}}]
|
simple_308
| false |
[{"name": "sports.match_schedule", "description": "Retrieve the match schedule for a specific sports team.", "parameters": {"type": "dict", "properties": {"team_name": {"type": "string", "description": "The name of the sports team."}, "num_matches": {"type": "integer", "description": "The number of upcoming matches you want to get."}, "league": {"type": "string", "description": "The sports league of the team. This is an optional parameter. Default is 'English Premier League'."}}, "required": ["team_name", "num_matches"]}}]
|
[{"type": "function", "function": {"name": "sports_match_schedule", "description": "Retrieve the match schedule for a specific sports team. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "properties": {"team_name": {"type": "string", "description": "The name of the sports team."}, "num_matches": {"type": "integer", "description": "The number of upcoming matches you want to get."}, "league": {"type": "string", "description": "The sports league of the team. This is an optional parameter. Default is 'English Premier League'."}}, "required": ["team_name", "num_matches"]}}}]
|
{}
|
{}
|
[] |
[[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'sports.match_schedule', 'description': 'Retrieve the match schedule for a specific sports team. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'properties': {'team_name': {'type': 'string', 'description': 'The name of the sports team.'}, 'num_matches': {'type': 'integer', 'description': 'The number of upcoming matches you want to get.'}, 'league': {'type': 'string', 'description': \"The sports league of the team. This is an optional parameter. Default is 'English Premier League'.\"}}, 'required': ['team_name', 'num_matches']}}]\n"}, {"role": "user", "content": "What are the next five matches for Manchester United and who are they playing against in the English Premier League?"}]]
|
Python
|
simple
|
simple
|
[{"sports.match_schedule": {"team_name": ["Manchester United", "Man United", "Man U", "MUFC"], "num_matches": [5], "league": ["English Premier League", ""]}}]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.