Spaces:
Sleeping
Sleeping
File size: 10,053 Bytes
26539b0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "d1e79cc0",
"metadata": {},
"outputs": [],
"source": [
"\"\"\"LangGraph Agent\"\"\"\n",
"import os\n",
"from dotenv import load_dotenv\n",
"from langgraph.graph import START, StateGraph, MessagesState\n",
"from langgraph.prebuilt import tools_condition\n",
"from langgraph.prebuilt import ToolNode\n",
"from langchain_google_genai import ChatGoogleGenerativeAI\n",
"from langchain_groq import ChatGroq\n",
"from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings\n",
"from langchain_community.tools.tavily_search import TavilySearchResults\n",
"from langchain_community.document_loaders import WikipediaLoader\n",
"from langchain_community.document_loaders import ArxivLoader\n",
"from langchain_community.vectorstores import SupabaseVectorStore\n",
"from langchain_core.messages import SystemMessage, HumanMessage\n",
"from langchain_core.tools import tool\n",
"from langchain.tools.retriever import create_retriever_tool\n",
"from supabase.client import Client, create_client\n",
"\n",
"load_dotenv()\n",
"\n",
"@tool\n",
"def multiply(a: int, b: int) -> int:\n",
" \"\"\"Multiply two numbers.\n",
" Args:\n",
" a: first int\n",
" b: second int\n",
" \"\"\"\n",
" return a * b\n",
"\n",
"@tool\n",
"def add(a: int, b: int) -> int:\n",
" \"\"\"Add two numbers.\n",
" \n",
" Args:\n",
" a: first int\n",
" b: second int\n",
" \"\"\"\n",
" return a + b\n",
"\n",
"@tool\n",
"def subtract(a: int, b: int) -> int:\n",
" \"\"\"Subtract two numbers.\n",
" \n",
" Args:\n",
" a: first int\n",
" b: second int\n",
" \"\"\"\n",
" return a - b\n",
"\n",
"@tool\n",
"def divide(a: int, b: int) -> int:\n",
" \"\"\"Divide two numbers.\n",
" \n",
" Args:\n",
" a: first int\n",
" b: second int\n",
" \"\"\"\n",
" if b == 0:\n",
" raise ValueError(\"Cannot divide by zero.\")\n",
" return a / b\n",
"\n",
"@tool\n",
"def modulus(a: int, b: int) -> int:\n",
" \"\"\"Get the modulus of two numbers.\n",
" \n",
" Args:\n",
" a: first int\n",
" b: second int\n",
" \"\"\"\n",
" return a % b\n",
"\n",
"@tool\n",
"def wiki_search(query: str) -> str:\n",
" \"\"\"Search Wikipedia for a query and return maximum 2 results.\n",
" \n",
" Args:\n",
" query: The search query.\"\"\"\n",
" search_docs = WikipediaLoader(query=query, load_max_docs=2).load()\n",
" formatted_search_docs = \"\\n\\n---\\n\\n\".join(\n",
" [\n",
" f'<Document source=\"{doc.metadata[\"source\"]}\" page=\"{doc.metadata.get(\"page\", \"\")}\"/>\\n{doc.page_content}\\n</Document>'\n",
" for doc in search_docs\n",
" ])\n",
" return {\"wiki_results\": formatted_search_docs}\n",
"\n",
"@tool\n",
"def web_search(query: str) -> str:\n",
" \"\"\"Search Tavily for a query and return maximum 3 results.\n",
" \n",
" Args:\n",
" query: The search query.\"\"\"\n",
" search_docs = TavilySearchResults(max_results=3).invoke(query=query)\n",
" formatted_search_docs = \"\\n\\n---\\n\\n\".join(\n",
" [\n",
" f'<Document source=\"{doc.metadata[\"source\"]}\" page=\"{doc.metadata.get(\"page\", \"\")}\"/>\\n{doc.page_content}\\n</Document>'\n",
" for doc in search_docs\n",
" ])\n",
" return {\"web_results\": formatted_search_docs}\n",
"\n",
"@tool\n",
"def arvix_search(query: str) -> str:\n",
" \"\"\"Search Arxiv for a query and return maximum 3 result.\n",
" \n",
" Args:\n",
" query: The search query.\"\"\"\n",
" search_docs = ArxivLoader(query=query, load_max_docs=3).load()\n",
" formatted_search_docs = \"\\n\\n---\\n\\n\".join(\n",
" [\n",
" f'<Document source=\"{doc.metadata[\"source\"]}\" page=\"{doc.metadata.get(\"page\", \"\")}\"/>\\n{doc.page_content[:1000]}\\n</Document>'\n",
" for doc in search_docs\n",
" ])\n",
" return {\"arvix_results\": formatted_search_docs}\n",
"\n",
"\n",
"\n",
"# load the system prompt from the file\n",
"with open(\"system_prompt.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" system_prompt = f.read()\n",
"\n",
"# System message\n",
"sys_msg = SystemMessage(content=system_prompt)\n",
"\n",
"# build a retriever\n",
"embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-mpnet-base-v2\") # dim=768\n",
"supabase_url = \"https://ajnakgegqblhwltzkzbz.supabase.co\"\n",
"supabase_key = \"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6ImFqbmFrZ2VncWJsaHdsdHpremJ6Iiwicm9sZSI6ImFub24iLCJpYXQiOjE3NDkyMDgxODgsImV4cCI6MjA2NDc4NDE4OH0.b9RPF-5otedg4yiaQu_uhOgYpXVXd9D_0oR-9cluUjo\"\n",
"\n",
"supabase: Client = create_client(supabase_url, supabase_key)\n",
"vector_store = SupabaseVectorStore(\n",
" client=supabase,\n",
" embedding= embeddings,\n",
" table_name=\"documents\",\n",
" query_name=\"match_documents_langchain\",\n",
")\n",
"create_retriever_tool = create_retriever_tool(\n",
" retriever=vector_store.as_retriever(),\n",
" name=\"Question Search\",\n",
" description=\"A tool to retrieve similar questions from a vector store.\",\n",
")\n",
"\n",
"\n",
"\n",
"tools = [\n",
" multiply,\n",
" add,\n",
" subtract,\n",
" divide,\n",
" modulus,\n",
" wiki_search,\n",
" web_search,\n",
" arvix_search,\n",
"]\n",
"\n",
"# Build graph function\n",
"def build_graph(provider: str = \"google\"):\n",
" \"\"\"Build the graph\"\"\"\n",
" # Load environment variables from .env file\n",
" if provider == \"google\":\n",
" # Google Gemini\n",
" llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\", temperature=0)\n",
" elif provider == \"groq\":\n",
" # Groq https://console.groq.com/docs/models\n",
" llm = ChatGroq(model=\"qwen-qwq-32b\",api_key=\"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\", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it\n",
" elif provider == \"huggingface\":\n",
" # TODO: Add huggingface endpoint\n",
" llm = ChatHuggingFace(\n",
" llm=HuggingFaceEndpoint(\n",
" url=\"https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf\",\n",
" temperature=0,\n",
" ),\n",
" )\n",
" else:\n",
" raise ValueError(\"Invalid provider. Choose 'google', 'groq' or 'huggingface'.\")\n",
" # Bind tools to LLM\n",
" llm_with_tools = llm.bind_tools(tools)\n",
"\n",
" # Node\n",
" def assistant(state: MessagesState):\n",
" \"\"\"Assistant node\"\"\"\n",
" return {\"messages\": [llm_with_tools.invoke(state[\"messages\"])]}\n",
" \n",
" # def retriever(state: MessagesState):\n",
" # \"\"\"Retriever node\"\"\"\n",
" # similar_question = vector_store.similarity_search(state[\"messages\"][0].content)\n",
" #example_msg = HumanMessage(\n",
" # content=f\"Here I provide a similar question and answer for reference: \\n\\n{similar_question[0].page_content}\",\n",
" # )\n",
" # return {\"messages\": [sys_msg] + state[\"messages\"] + [example_msg]}\n",
"\n",
" from langchain_core.messages import AIMessage\n",
"\n",
" def retriever(state: MessagesState):\n",
" query = state[\"messages\"][-1].content\n",
" similar_doc = vector_store.similarity_search(query, k=1)[0]\n",
"\n",
" content = similar_doc.page_content\n",
" if \"Final answer :\" in content:\n",
" answer = content.split(\"Final answer :\")[-1].strip()\n",
" else:\n",
" answer = content.strip()\n",
"\n",
" return {\"messages\": [AIMessage(content=answer)]}\n",
"\n",
" # builder = StateGraph(MessagesState)\n",
" #builder.add_node(\"retriever\", retriever)\n",
" #builder.add_node(\"assistant\", assistant)\n",
" #builder.add_node(\"tools\", ToolNode(tools))\n",
" #builder.add_edge(START, \"retriever\")\n",
" #builder.add_edge(\"retriever\", \"assistant\")\n",
" #builder.add_conditional_edges(\n",
" # \"assistant\",\n",
" # tools_condition,\n",
" #)\n",
" #builder.add_edge(\"tools\", \"assistant\")\n",
"\n",
" builder = StateGraph(MessagesState)\n",
" builder.add_node(\"retriever\", retriever)\n",
"\n",
" # Retriever ist Start und Endpunkt\n",
" builder.set_entry_point(\"retriever\")\n",
" builder.set_finish_point(\"retriever\")\n",
"\n",
" # Compile graph\n",
" return builder.compile()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "abc55916",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|