language_models

Input/output interface for a language model.

Registry mapping model identifiers or names to their ModelProfile.

Import an attribute from a module located in a package.

This utility function is used in custom __getattr__ methods within __init__.py files to dynamically import attributes.

Check whether a block contains multimodal data in OpenAI Chat Completions format.

Supports both data and ID-style blocks (e.g. 'file_data' and 'file_id')

If additional keys are present, they are ignored / will not affect outcome as long as the required keys are present and valid.

Get a GPT-2 tokenizer instance.

This function is cached to avoid re-loading the tokenizer every time it is called.

Abstract base class for interfacing with language models.

All language model wrappers inherited from BaseLanguageModel.

LangSmith parameters for tracing.

Base class for chat models.

Simplified implementation for a chat model to inherit from.

Fake LLM for testing purposes.

Fake streaming list LLM for testing purposes.

An LLM that will return responses from a list in order.

This model also supports optionally sleeping between successive chunks in a streaming implementation.

Fake chat model for testing purposes.

Fake chat model for testing purposes.

Generic fake chat model that can be used to test the chat model interface.

• Chat model should be usable in both sync and async tests
• Invokes on_llm_new_token to allow for testing of callback related code for new tokens.
• Includes logic to break messages into message chunk to facilitate testing of streaming.

Generic fake chat model that can be used to test the chat model interface.

• Chat model should be usable in both sync and async tests

Simple interface for implementing a custom LLM.

You should subclass this class and implement the following:

• _call method: Run the LLM on the given prompt and input (used by invoke).
• _identifying_params property: Return a dictionary of the identifying parameters This is critical for caching and tracing purposes. Identifying parameters is a dict that identifies the LLM. It should mostly include a model_name.

Optional: Override the following methods to provide more optimizations:

• _acall: Provide a native async version of the _call method. If not provided, will delegate to the synchronous version using run_in_executor. (Used by ainvoke).
• _stream: Stream the LLM on the given prompt and input. stream will use _stream if provided, otherwise it use _call and output will arrive in one chunk.
• _astream: Override to provide a native async version of the _stream method. astream will use _astream if provided, otherwise it will implement a fallback behavior that will use _stream if _stream is implemented, and use _acall if _stream is not implemented.

Base LLM abstract interface.

It should take in a prompt and return a string.

Model profile.

Provides information about chat model capabilities, such as context window sizes and supported features.

Input to a language model.

Output from a language model.

Base interface for traditional large language models (LLMs) to expose.

These are traditionally older models (newer models generally are chat models).

Base language models class.

Fake chat models for testing purposes.

Chat models for conversational AI.

Model profile types and utilities.

Per-message streaming objects for content-block protocol events.

ChatModelStream is the synchronous variant returned by BaseChatModel.stream_v2(). AsyncChatModelStream is the asynchronous variant returned by BaseChatModel.astream_v2().

Both expose typed projection properties (.text, .reasoning, .tool_calls, .usage, .output) that accumulate protocol events as they arrive. Projections can be iterated for deltas or drained for the final accumulated value.

Raw protocol events are also available via direct iteration on the stream object (replay-buffer semantics — multiple independent consumers supported).

Fake LLMs for testing purposes.