langchain

You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

History

Igor Drozdov b664dbcc36 feat(community): add support for tool_calls response (#23765 ) When `model_kwargs={"tools": tools}` are passed to `ChatLiteLLM`, they are executed, but the response is not recognized correctly Let's add `tool_calls` to the `additional_kwargs` Thank you for contributing to LangChain! ## ChatAnthropic I used the following example to verify the output of llm with tools: ```python from langchain_core.pydantic_v1 import BaseModel, Field from langchain_anthropic import ChatAnthropic class GetWeather(BaseModel): '''Get the current weather in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") class GetPopulation(BaseModel): '''Get the current population in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") llm = ChatAnthropic(model="claude-3-sonnet-20240229") llm_with_tools = llm.bind_tools([GetWeather, GetPopulation]) ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?") print(ai_msg.tool_calls) ``` I get the following response: ```json [{'name': 'GetWeather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_01UfDA89knrhw3vFV9X47neT'}, {'name': 'GetWeather', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01NrYVRYae7m7z7tBgyPb3Gd'}, {'name': 'GetPopulation', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_01EPFEpDgzL6vV2dTpD9SVP5'}, {'name': 'GetPopulation', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01B5J6tPJXgwwfhQX9BHP2dt'}] ``` ## LiteLLM Based on https://litellm.vercel.app/docs/completion/function_call ```python from langchain_core.pydantic_v1 import BaseModel, Field from langchain_core.utils.function_calling import convert_to_openai_tool import litellm class GetWeather(BaseModel): '''Get the current weather in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") class GetPopulation(BaseModel): '''Get the current population in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") prompt = "Which city is hotter today and which is bigger: LA or NY?" tools = [convert_to_openai_tool(GetWeather), convert_to_openai_tool(GetPopulation)] response = litellm.completion(model="claude-3-sonnet-20240229", messages=[{'role': 'user', 'content': prompt}], tools=tools) print(response.choices[0].message.tool_calls) ``` ```python [ChatCompletionMessageToolCall(function=Function(arguments='{"location": "Los Angeles, CA"}', name='GetWeather'), id='toolu_01HeDWV5vP7BDFfytH5FJsja', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "New York, NY"}', name='GetWeather'), id='toolu_01EiLesUSEr3YK1DaE2jxsQv', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "Los Angeles, CA"}', name='GetPopulation'), id='toolu_01Xz26zvkBDRxEUEWm9pX6xa', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "New York, NY"}', name='GetPopulation'), id='toolu_01SDqKnsLjvUXuBsgAZdEEpp', type='function')] ``` ## ChatLiteLLM When I try the following ```python from langchain_core.pydantic_v1 import BaseModel, Field from langchain_core.utils.function_calling import convert_to_openai_tool from langchain_community.chat_models import ChatLiteLLM class GetWeather(BaseModel): '''Get the current weather in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") class GetPopulation(BaseModel): '''Get the current population in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") prompt = "Which city is hotter today and which is bigger: LA or NY?" tools = [convert_to_openai_tool(GetWeather), convert_to_openai_tool(GetPopulation)] llm = ChatLiteLLM(model="claude-3-sonnet-20240229", model_kwargs={"tools": tools}) ai_msg = llm.invoke(prompt) print(ai_msg) print(ai_msg.tool_calls) ``` ```python content="Okay, let's find out the current weather and populations for Los Angeles and New York City:" response_metadata={'token_usage': Usage(prompt_tokens=329, completion_tokens=193, total_tokens=522), 'model': 'claude-3-sonnet-20240229', 'finish_reason': 'tool_calls'} id='run-748b7a84-84f4-497e-bba1-320bd4823937-0' [] ``` --- When I apply the changes of this PR, the output is ```json [{'name': 'GetWeather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_017D2tGjiaiakB1HadsEFZ4e'}, {'name': 'GetWeather', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01WrDpJfVqLkPejWzonPCbLW'}, {'name': 'GetPopulation', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_016UKyYrVAV9Pz99iZGgGU7V'}, {'name': 'GetPopulation', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01Sgv1imExFX1oiR1Cw88zKy'}] ``` If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. Co-authored-by: Igor Drozdov <idrozdov@gitlab.com>		3 months ago
..
__init__.py	Add OCI Generative AI new model support (#22880 )	3 months ago
anthropic.py	(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265 )	5 months ago
anyscale.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
azure_openai.py	infra: rm unused # noqa violations (#22049 )	4 months ago
azureml_endpoint.py	infra: rm unused # noqa violations (#22049 )	4 months ago
baichuan.py	community[patch]: Update root_validators ChatModels: ChatBaichuan, QianfanChatEndpoint, MiniMaxChat, ChatSparkLLM, ChatZhipuAI (#22853 )	3 months ago
baidu_qianfan_endpoint.py	community[patch]: set tool name for tongyi&qianfan llm (#22889 )	3 months ago
bedrock.py	community[patch]: Fix message formatting for Anthropic models on Amazon Bedrock (#20801 )	5 months ago
cohere.py	(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265 )	5 months ago
coze.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
dappier.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
databricks.py	community[patch]: Update documentation string in databricks chat model (#21915 )	4 months ago
deepinfra.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
edenai.py	community[minor]: Add tools calls to `ChatEdenAI` (#22320 )	4 months ago
ernie.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
everlyai.py	community[minor]: import fix (#20995 )	5 months ago
fake.py	community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463 )	10 months ago
fireworks.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
friendli.py	community[minor]: Integration for `Friendli` LLM and `ChatFriendli` ChatModel. (#17913 )	7 months ago
gigachat.py	community[patch]: upgrade to recent version of mypy (#21616 )	4 months ago
google_palm.py	Refactor: use SecretStr for palm chat-model (#15100 )	9 months ago
gpt_router.py	community[patch]: callback before yield for _stream/_astream (#17907 )	7 months ago
huggingface.py	community[patch]: Update root_validators to use pre=True or pre=False (#23731 )	3 months ago
human.py	infra: add print rule to ruff (#16221 )	8 months ago
hunyuan.py	community[patch]: fix hunyuan message include chinese signature error (#22795 ) (#22796 )	3 months ago
javelin_ai_gateway.py	community[patch]: standardize init args, update for javelin sdk release. (#21980 )	4 months ago
jinachat.py	community[patch]: upgrade to recent version of mypy (#21616 )	4 months ago
kinetica.py	community[patch]: type ignore fixes (#18395 )	7 months ago
konko.py	community[minor]: import fix (#20995 )	5 months ago
litellm.py	feat(community): add support for tool_calls response (#23765 )	3 months ago
litellm_router.py	community[patch]: callback before yield for _stream/_astream (#17907 )	7 months ago
llama_edge.py	community[patch]: upgrade to recent version of mypy (#21616 )	4 months ago
llamacpp.py	openai, anthropic, ...: with_structured_output to pass in explicit tool choice (#23645 )	3 months ago
maritalk.py	community: fix lint (#23611 )	3 months ago
meta.py	docs: docstrings `langchain_community` update (#14889 )	9 months ago
minimax.py	community[patch]: Update root_validators ChatModels: ChatBaichuan, QianfanChatEndpoint, MiniMaxChat, ChatSparkLLM, ChatZhipuAI (#22853 )	3 months ago
mlflow.py	community[patch]: Fix ChatDatabricsk in case that streaming response doesn't have role field in delta chunk (#21897 )	4 months ago
mlflow_ai_gateway.py	community[patch]: chat model mypy fixes (#17061 )	8 months ago
mlx.py	docs: community docstring updates (#21040 )	5 months ago
moonshot.py	fix: MoonshotChat fails when setting the moonshot_api_key through the OS environment. (#23176 )	3 months ago
oci_generative_ai.py	Add OCI Generative AI new model support (#22880 )	3 months ago
octoai.py	community[minor]: add ChatOctoAI (#20059 )	5 months ago
ollama.py	Ollama vision support (#22734 )	3 months ago
openai.py	Standardized openai init params (#21739 )	4 months ago
pai_eas_endpoint.py	community[patch]: Update root_validators embeddings: llamacpp, jina, dashscope, mosaicml, huggingface_hub, Toolkits: Connery, ChatModels: PAI_EAS, (#22828 )	3 months ago
perplexity.py	docs: updated PPLX model (#23723 )	3 months ago
premai.py	community[minor]: Prem Templates (#22783 )	3 months ago
promptlayer_openai.py	docs: use standard openai params (#20160 )	6 months ago
snowflake.py	community[minor]: add `ChatSnowflakeCortex` chat model (#21490 )	3 months ago
solar.py	community[patch]: upgrade to recent version of mypy (#21616 )	4 months ago
sparkllm.py	community[patch]: Update root_validators ChatModels: ChatBaichuan, QianfanChatEndpoint, MiniMaxChat, ChatSparkLLM, ChatZhipuAI (#22853 )	3 months ago
tongyi.py	community[patch]: set tool name for tongyi&qianfan llm (#22889 )	3 months ago
vertexai.py	(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265 )	5 months ago
volcengine_maas.py	community[patch]: add stop parameter support to volcengine maas (#19052 )	6 months ago
yandex.py	community[patch]: docstrings update (#20301 )	6 months ago
yuan2.py	community[patch]: upgrade to recent version of mypy (#21616 )	4 months ago
zhipuai.py	community[patch]: Invoke callback prior to yielding token (#23638 )	3 months ago