from_llm_and_tools() — langchain Function Reference

Architecture documentation for the from_llm_and_tools() function in base.py from the langchain codebase.

Function python AgentOrchestration ToolInterface calls 3 called by 1

Entity Profile

AgentOrchestration→ ToolInterface→ from_llm_and_tools() — langchain Function Reference

Dependency Diagram

graph TD
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059["from_llm_and_tools()"]
  efa737fc_e2bb_00c6_fe6e_ee6cb1f6cb6c["ZeroShotAgent"]
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059 -->|defined in| efa737fc_e2bb_00c6_fe6e_ee6cb1f6cb6c
  d76c1f53_4db7_bb60_a9d5_23fc16890cf0["from_chains()"]
  d76c1f53_4db7_bb60_a9d5_23fc16890cf0 -->|calls| f50a836d_579d_7ed4_e51f_6bb4bd0b8059
  1c25b3ee_1cc2_569b_6970_bd431e6f54ca["_validate_tools()"]
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059 -->|calls| 1c25b3ee_1cc2_569b_6970_bd431e6f54ca
  a98a6213_7754_f1a3_d0c4_c6068b628192["create_prompt()"]
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059 -->|calls| a98a6213_7754_f1a3_d0c4_c6068b628192
  66bbb2d3_d68f_0d1b_d3bc_2f021869e9e1["_get_default_output_parser()"]
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059 -->|calls| 66bbb2d3_d68f_0d1b_d3bc_2f021869e9e1
  style f50a836d_579d_7ed4_e51f_6bb4bd0b8059 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/mrkl/base.py lines 114–159

    def from_llm_and_tools(
        cls,
        llm: BaseLanguageModel,
        tools: Sequence[BaseTool],
        callback_manager: BaseCallbackManager | None = None,
        output_parser: AgentOutputParser | None = None,
        prefix: str = PREFIX,
        suffix: str = SUFFIX,
        format_instructions: str = FORMAT_INSTRUCTIONS,
        input_variables: list[str] | None = None,
        **kwargs: Any,
    ) -> Agent:
        """Construct an agent from an LLM and tools.

        Args:
            llm: The LLM to use as the agent LLM.
            tools: The tools to use.
            callback_manager: The callback manager to use.
            output_parser: The output parser to use.
            prefix: The prefix to use.
            suffix: The suffix to use.
            format_instructions: The format instructions to use.
            input_variables: The input variables to use.
            kwargs: Additional parameters to pass to the agent.
        """
        cls._validate_tools(tools)
        prompt = cls.create_prompt(
            tools,
            prefix=prefix,
            suffix=suffix,
            format_instructions=format_instructions,
            input_variables=input_variables,
        )
        llm_chain = LLMChain(
            llm=llm,
            prompt=prompt,
            callback_manager=callback_manager,
        )
        tool_names = [tool.name for tool in tools]
        _output_parser = output_parser or cls._get_default_output_parser()
        return cls(
            llm_chain=llm_chain,
            allowed_tools=tool_names,
            output_parser=_output_parser,
            **kwargs,
        )