langchain

Commit Graph

Author	SHA1	Message	Date
Bagatur	d96f67b06f	standard-tests[patch]: Update chat model standard tests (#22378 ) - Refactor standard test classes to make them easier to configure - Update openai to support stop_sequences init param - Update groq to support stop_sequences init param - Update fireworks to support max_retries init param - Update ChatModel.bind_tools to type tool_choice - Update groq to handle tool_choice="any". this may be controversial --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 months ago
ccurme	936aedd10c	mistral[patch]: add usage_metadata to (a)invoke and (a)stream (#22781 )	3 months ago
ccurme	fbfed65fb1	core, partners: add token usage attribute to AIMessage (#21944 ) ```python class UsageMetadata(TypedDict): """Usage metadata for a message, such as token counts. Attributes: input_tokens: (int) count of input (or prompt) tokens output_tokens: (int) count of output (or completion) tokens total_tokens: (int) total token count """ input_tokens: int output_tokens: int total_tokens: int ``` ```python class AIMessage(BaseMessage): ... usage_metadata: Optional[UsageMetadata] = None """If provided, token usage information associated with the message.""" ... ```	4 months ago
ccurme	9c76739425	mistral: implement ls_params (#21867 )	4 months ago
ccurme	181dfef118	core, standard tests, partner packages: add test for model params (#21677 ) 1. Adds `.get_ls_params` to BaseChatModel which returns ```python class LangSmithParams(TypedDict, total=False): ls_provider: str ls_model_name: str ls_model_type: Literal["chat"] ls_temperature: Optional[float] ls_max_tokens: Optional[int] ls_stop: Optional[List[str]] ``` by default it will only return ```python {ls_model_type="chat", ls_stop=stop} ``` 2. Add these params to inheritable metadata in `CallbackManager.configure` 3. Implement `.get_ls_params` and populate all params for Anthropic + all subclasses of BaseChatOpenAI Sample trace: https://smith.langchain.com/public/d2962673-4c83-47c7-b51e-61d07aaffb1b/r OpenAI: <img width="984" alt="Screenshot 2024-05-17 at 10 03 35 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/2ef41f74-a9df-4e0e-905d-da74fa82a910"> Anthropic: <img width="978" alt="Screenshot 2024-05-17 at 10 06 07 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/39701c9f-7da5-4f1a-ab14-84e9169d63e7"> Mistral (and all others for which params are not yet populated): <img width="977" alt="Screenshot 2024-05-17 at 10 08 43 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/37d7d894-fec2-4300-986f-49a5f0191b03">	4 months ago
Maxime Perrin	1ebb5a70ad	partners(mistralai): Removing unused variable in completion request (using tool_calls or content) (#21201 ) This PR fixes #21196. The error was occurring when calling chat completion API with a chat history. Indeed, the Mistral API does not accept both `content` and `tool_calls` in the same body. This PR removes one of theses variables depending on the necessity. --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr> Co-authored-by: Chester Curme <chester.curme@gmail.com>	5 months ago
ccurme	fdabd3cdf5	mistral, openai: support custom tokenizers in chat models (#20901 )	5 months ago
ccurme	4a17951900	mistral: read tool calls from AIMessage (#20554 ) Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
ccurme	795c728f71	mistral[patch]: add IDs to tool calls (#20299 ) Mistral gives us one ID per response, no individual IDs for tool calls. ```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_mistralai import ChatMistralAI prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatMistralAI(model="mistral-large-latest", temperature=0) @tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2 tools = [magic_function] agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True) agent_executor.invoke({"input": "what is the value of magic_function(3)?"}) ``` --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
Bagatur	9514bc4d67	core[minor], ...: add tool calls message (#18947 ) core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor] ```python class ToolCall(TypedDict): name: str args: Dict[str, Any] id: Optional[str] class InvalidToolCall(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] error: Optional[str] class ToolCallChunk(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] index: Optional[int] class AIMessage(BaseMessage): ... tool_calls: List[ToolCall] = [] invalid_tool_calls: List[InvalidToolCall] = [] ... class AIMessageChunk(AIMessage, BaseMessageChunk): ... tool_call_chunks: Optional[List[ToolCallChunk]] = None ... ``` Important considerations: - Parsing logic occurs within different providers; - ~Changing output type is a breaking change for anyone doing explicit type checking;~ - ~Langsmith rendering will need to be updated: https://github.com/langchain-ai/langchainplus/pull/3561~ - ~Langserve will need to be updated~ - Adding chunks: - ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has non-null .tool_calls.~ - Tool call chunks are appended, merging when having equal values of `index`. - additional_kwargs accumulate the normal way. - During streaming: - ~Messages can change types (e.g., from AIMessageChunk to AIToolCallsMessageChunk)~ - Output parsers parse additional_kwargs (during .invoke they read off tool calls). Packages outside of `partners/`: - https://github.com/langchain-ai/langchain-cohere/pull/7 - https://github.com/langchain-ai/langchain-google/pull/123/files --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	5 months ago
Erick Friis	855ba46f80	standard-tests: a standard unit and integration test set (#20182 ) just chat models for now	6 months ago
Bagatur	3490d70238	mistralai[patch]: standardize model params (#20163 ) Related to #20085	6 months ago
Bagatur	2f5606a318	mistralai[patch]: correct integration_test (#19774 )	6 months ago
Pierre Véron	ace7b66261	mistralai[patch]: add missing _combine_llm_outputs implementation in ChatMistralAI (#18603 ) # Description Implementing `_combine_llm_outputs` to `ChatMistralAI` to override the default implementation in `BaseChatModel` returning `{}`. The implementation is inspired by the one in `ChatOpenAI` from package `langchain-openai`. # Issue None # Dependencies None # Twitter handle None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Erick Friis	b617085af0	mistralai[patch]: streaming tool calls (#19469 )	6 months ago
Erick Friis	11e37943ed	mistralai[patch]: fix core version (#19454 )	6 months ago
ccurme	c4599444ee	mistralai: update tool calling (#19451 ) ```python from langchain.agents import tool from langchain_mistralai import ChatMistralAI llm = ChatMistralAI(model="mistral-large-latest", temperature=0) @tool def get_word_length(word: str) -> int: """Returns the length of a word.""" return len(word) tools = [get_word_length] llm_with_tools = llm.bind_tools(tools) llm_with_tools.invoke("how long is the word chrysanthemum") ``` currently raises ``` AttributeError: 'dict' object has no attribute 'model_dump' ``` Same with `.with_structured_output` ```python from langchain_mistralai import ChatMistralAI from langchain_core.pydantic_v1 import BaseModel class AnswerWithJustification(BaseModel): """An answer to the user question along with justification for the answer.""" answer: str justification: str llm = ChatMistralAI(model="mistral-large-latest", temperature=0) structured_llm = llm.with_structured_output(AnswerWithJustification) structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers") ``` This appears to fix.	6 months ago
Erick Friis	53ac1ebbbc	mistralai[minor]: 0.1.0rc0, remove mistral sdk (#19420 )	6 months ago
Erick Friis	f881a3330c	mistralai[patch]: 16k token batching logic embed (#17136 )	8 months ago
ccurme	0826d87ecd	langchain_mistralai[patch]: Invoke callback prior to yielding token (#16986 ) - Description: Invoke callback prior to yielding token in stream and astream methods for ChatMistralAI. - Issue: https://github.com/langchain-ai/langchain/issues/16913	8 months ago
Erick Friis	65b231d40b	mistralai[patch]: async integration tests (#16214 )	8 months ago
David	c323742f4f	mistralai[minor]: Add embeddings (#15282 ) - Description: Adds MistralAIEmbeddings class for embeddings, using the new official API. - Dependencies: mistralai - Tag maintainer: @efriis, @hwchase17 - Twitter handle: @LMS_David_RS Create `integrations/text_embedding/mistralai.ipynb`: an example notebook for MistralAIEmbeddings class Modify `embeddings/__init__.py`: Import the class Create `embeddings/mistralai.py`: The embedding class Create `integration_tests/embeddings/test_mistralai.py`: The test file. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Bagatur	a5be9f9475	mistralai: Add langchain-mistralai partner package (#14783 ) Co-authored-by: Chad Phillips <chad@apartmentlines.com>	9 months ago

23 Commits (9b3a025f9c806a6f8a00030c7058c689536ae5a0)