You forgot about ChatMLX.bind_tools

[svnv-svsv-jm]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_community.chat_models.mlx import ChatMLX
from langgraph.prebuilt import create_react_agent

tools = ...

agent_executor = create_react_agent(ChatMLX(...), tools)

NotImplementedError

Error Message and Stack Trace (if applicable)

No response

Description

You forgot to implement the bind_tools method for the ChatMLX class.

I was getting a NotImplementedError when trying to create a react agent:

from langchain_community.chat_models.mlx import ChatMLX
from langgraph.prebuilt import create_react_agent

agent_executor = create_react_agent(ChatMLX(...), tools)

Knowing that this works when I do agent_executor = create_react_agent(ChatHuggingFace(...), tools), I just copied the method ChatHuggingFace.bind_tools and extended the ChatMLX class with it, and not only I was able to create the agent, but also to .invoke() it!

See:

import typing as ty

from langchain_community.chat_models.mlx import ChatMLX as ChatMLX_
from langchain_core.tools import BaseTool
from langchain_core.runnables import Runnable
from langchain_core.language_models import LanguageModelInput
from langchain_core.utils.function_calling import convert_to_openai_tool

class ChatMLX(ChatMLX_):
    """We patch the original class by adding the `bind_tools` method."""

# THIS IS COPIED FROM `ChatHuggingFace.bind_tools`
    def bind_tools(
        self,
        tools: ty.Sequence[ty.Union[dict[str, ty.Any], type, ty.Callable, BaseTool]],
        *,
        tool_choice: ty.Optional[ty.Union[dict, str, ty.Literal["auto", "none"], bool]] = None,
        **kwargs: ty.Any,
    ) -> Runnable[LanguageModelInput, BaseMessage]:
        """Bind tool-like objects to this chat model.

        Assumes model is compatible with OpenAI tool-calling API.

        Args:
            tools: A list of tool definitions to bind to this chat model.
                Supports any tool definition handled by
                :meth:`langchain_core.utils.function_calling.convert_to_openai_tool`.
            tool_choice: Which tool to require the model to call.
                Must be the name of the single provided function or
                "auto" to automatically determine which function to call
                (if any), or a dict of the form:
                {"type": "function", "function": {"name": <<tool_name>>}}.
            **kwargs: Any additional parameters to pass to the
                :class:`~langchain.runnable.Runnable` constructor.
        """
        formatted_tools = [convert_to_openai_tool(tool) for tool in tools]
        if tool_choice is not None and tool_choice:
            if len(formatted_tools) != 1:
                raise ValueError(
                    "When specifying `tool_choice`, you must provide exactly one "
                    f"tool. Received {len(formatted_tools)} tools."
                )
            if isinstance(tool_choice, str):
                if tool_choice not in ("auto", "none"):
                    tool_choice = {
                        "type": "function",
                        "function": {"name": tool_choice},
                    }
            elif isinstance(tool_choice, bool):
                tool_choice = formatted_tools[0]
            elif isinstance(tool_choice, dict):
                if formatted_tools[0]["function"]["name"] != tool_choice["function"]["name"]:
                    raise ValueError(
                        f"Tool choice {tool_choice} was specified, but the only "
                        f"provided tool was {formatted_tools[0]['function']['name']}."
                    )
            else:
                raise ValueError(
                    f"Unrecognized tool_choice type. Expected str, bool or dict. " f"Received: {tool_choice}"
                )
            kwargs["tool_choice"] = tool_choice
        return super().bind(tools=formatted_tools, **kwargs)

I think you should create a small PR where this method is added to the ChatMLX class, perhaps avoiding code duplication.

I'd do it myself but I do not have time, the owners of this repo can do it very quickly.

System Info

System Information
------------------
> OS:  Darwin
> OS Version:  Darwin Kernel Version 24.1.0: Thu Oct 10 21:05:14 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T8103
> Python Version:  3.12.7 (main, Nov 20 2024, 14:24:14) [Clang 16.0.0 (clang-1600.0.26.4)]

Package Information
-------------------
> langchain_core: 0.3.21
> langchain: 0.3.9
> langchain_community: 0.3.9
> langsmith: 0.1.147
> langchain_huggingface: 0.1.2
> langchain_ollama: 0.2.1
> langchain_openai: 0.2.11
> langchain_text_splitters: 0.3.2
> langgraph_sdk: 0.1.43

Optional packages not installed
-------------------------------
> langserve

Other Dependencies
------------------
> aiohttp: 3.11.9
> async-timeout: Installed. No version info available.
> dataclasses-json: 0.6.7
> httpx: 0.27.2
> httpx-sse: 0.4.0
> huggingface-hub: 0.24.7
> jsonpatch: 1.33
> langsmith-pyo3: Installed. No version info available.
> numpy: 1.26.4
> ollama: 0.4.2
> openai: 1.56.2
> orjson: 3.10.12
> packaging: 24.2
> pydantic: 2.10.3
> pydantic-settings: 2.6.1
> PyYAML: 6.0.2
> requests: 2.32.3
> requests-toolbelt: 1.0.0
> sentence-transformers: 2.7.0
> SQLAlchemy: 2.0.36
> tenacity: 8.4.2
> tiktoken: 0.8.0
> tokenizers: 0.20.3
> transformers: 4.46.3
> typing-extensions: 4.12.2

[ccurme]

Should be addressed in #28743