Home / Function/ bind_tools() — langchain Function Reference

bind_tools() — langchain Function Reference

Architecture documentation for the bind_tools() function in chat_models.py from the langchain codebase.

Entity Profile

Dependency Diagram

graph TD
  28eecd69_58db_770a_6b8b_ddbe1d0c5e20["bind_tools()"]
  24cf3ac3_ed46_66ab_27f4_5b5d67f0b7f0["ChatMistralAI"]
  28eecd69_58db_770a_6b8b_ddbe1d0c5e20 -->|defined in| 24cf3ac3_ed46_66ab_27f4_5b5d67f0b7f0
  f73f8b04_5858_f84e_8eb8_98cd9e9ef152["with_structured_output()"]
  f73f8b04_5858_f84e_8eb8_98cd9e9ef152 -->|calls| 28eecd69_58db_770a_6b8b_ddbe1d0c5e20
  style 28eecd69_58db_770a_6b8b_ddbe1d0c5e20 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/mistralai/langchain_mistralai/chat_models.py lines 784–823

    def bind_tools(
        self,
        tools: Sequence[dict[str, Any] | type | Callable | BaseTool],
        tool_choice: dict | str | Literal["auto", "any"] | None = None,  # noqa: PYI051
        **kwargs: Any,
    ) -> Runnable[LanguageModelInput, AIMessage]:
        """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 [`convert_to_openai_tool`][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 are passed directly to
                `self.bind(**kwargs)`.
        """  # noqa: E501
        formatted_tools = [convert_to_openai_tool(tool) for tool in tools]
        if tool_choice:
            tool_names = []
            for tool in formatted_tools:
                if ("function" in tool and (name := tool["function"].get("name"))) or (
                    name := tool.get("name")
                ):
                    tool_names.append(name)
                else:
                    pass
            if tool_choice in tool_names:
                kwargs["tool_choice"] = {
                    "type": "function",
                    "function": {"name": tool_choice},
                }
            else:
                kwargs["tool_choice"] = tool_choice
        return super().bind(tools=formatted_tools, **kwargs)

Domain

Subdomains

Frequently Asked Questions

What does bind_tools() do?
bind_tools() is a function in the langchain codebase, defined in libs/partners/mistralai/langchain_mistralai/chat_models.py.
Where is bind_tools() defined?
bind_tools() is defined in libs/partners/mistralai/langchain_mistralai/chat_models.py at line 784.
What calls bind_tools()?
bind_tools() is called by 1 function(s): with_structured_output.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free