Spaces:
Sleeping
Sleeping
File size: 5,147 Bytes
94ff58a |
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 |
import json
import logging
from openai import OpenAI
import pdb
from langchain_openai import ChatOpenAI
from langchain_core.globals import get_llm_cache
from langchain_core.language_models.base import (
BaseLanguageModel,
LangSmithParams,
LanguageModelInput,
)
from langchain_core.load import dumpd, dumps
from langchain_core.messages import (
AIMessage,
SystemMessage,
AnyMessage,
BaseMessage,
BaseMessageChunk,
HumanMessage,
convert_to_messages,
message_chunk_to_message,
)
from langchain_core.outputs import (
ChatGeneration,
ChatGenerationChunk,
ChatResult,
LLMResult,
RunInfo,
)
from langchain_ollama import ChatOllama
from langchain_core.output_parsers.base import OutputParserLike
from langchain_core.runnables import Runnable, RunnableConfig
from langchain_core.tools import BaseTool
from typing import (
TYPE_CHECKING,
Any,
Callable,
Literal,
Optional,
Union,
cast,
)
logger = logging.getLogger(__name__)
class DeepSeekR1ChatOpenAI(ChatOpenAI):
def __init__(self, *args: Any, **kwargs: Any) -> None:
super().__init__(*args, **kwargs)
self.client = OpenAI(
base_url=kwargs.get("base_url"),
api_key=kwargs.get("api_key")
)
async def ainvoke(
self,
input: LanguageModelInput,
config: Optional[RunnableConfig] = None,
*,
stop: Optional[list[str]] = None,
**kwargs: Any,
) -> AIMessage:
message_history = []
for input_ in input:
if isinstance(input_, SystemMessage):
message_history.append({"role": "system", "content": input_.content})
elif isinstance(input_, AIMessage):
message_history.append({"role": "assistant", "content": input_.content})
else:
message_history.append({"role": "user", "content": input_.content})
# Log messages before API call
logger.info("\n📤 Messages being sent to API:")
logger.info(json.dumps(message_history, indent=2))
logger.info("-" * 50)
# TODO: This is where the LLM is called
response = self.client.chat.completions.create(
model=self.model_name,
messages=message_history
)
reasoning_content = response.choices[0].message.reasoning_content
content = response.choices[0].message.content
return AIMessage(content=content, reasoning_content=reasoning_content)
def invoke(
self,
input: LanguageModelInput,
config: Optional[RunnableConfig] = None,
*,
stop: Optional[list[str]] = None,
**kwargs: Any,
) -> AIMessage:
message_history = []
for input_ in input:
if isinstance(input_, SystemMessage):
message_history.append({"role": "system", "content": input_.content})
elif isinstance(input_, AIMessage):
message_history.append({"role": "assistant", "content": input_.content})
else:
message_history.append({"role": "user", "content": input_.content})
# Log messages before API call
logger.info("\n📤 Messages being sent to API:")
logger.info(json.dumps(message_history, indent=2))
logger.info("-" * 50)
# TODO: This is where the LLM is called
response = self.client.chat.completions.create(
model=self.model_name,
messages=message_history
)
reasoning_content = response.choices[0].message.reasoning_content
content = response.choices[0].message.content
return AIMessage(content=content, reasoning_content=reasoning_content)
class DeepSeekR1ChatOllama(ChatOllama):
async def ainvoke(
self,
input: LanguageModelInput,
config: Optional[RunnableConfig] = None,
*,
stop: Optional[list[str]] = None,
**kwargs: Any,
) -> AIMessage:
org_ai_message = await super().ainvoke(input=input)
org_content = org_ai_message.content
reasoning_content = org_content.split("</think>")[0].replace("<think>", "")
content = org_content.split("</think>")[1]
if "**JSON Response:**" in content:
content = content.split("**JSON Response:**")[-1]
return AIMessage(content=content, reasoning_content=reasoning_content)
def invoke(
self,
input: LanguageModelInput,
config: Optional[RunnableConfig] = None,
*,
stop: Optional[list[str]] = None,
**kwargs: Any,
) -> AIMessage:
org_ai_message = super().invoke(input=input)
org_content = org_ai_message.content
reasoning_content = org_content.split("</think>")[0].replace("<think>", "")
content = org_content.split("</think>")[1]
if "**JSON Response:**" in content:
content = content.split("**JSON Response:**")[-1]
return AIMessage(content=content, reasoning_content=reasoning_content)
|