from_chains() — langchain Function Reference

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

Function python AgentOrchestration ToolInterface calls 1

Entity Profile

AgentOrchestration→ ToolInterface→ from_chains() — langchain Function Reference

Dependency Diagram

graph TD
  d76c1f53_4db7_bb60_a9d5_23fc16890cf0["from_chains()"]
  32fdcb01_4c25_5670_f8e5_6fa8ce84181e["MRKLChain"]
  d76c1f53_4db7_bb60_a9d5_23fc16890cf0 -->|defined in| 32fdcb01_4c25_5670_f8e5_6fa8ce84181e
  f50a836d_579d_7ed4_e51f_6bb4bd0b8059["from_llm_and_tools()"]
  d76c1f53_4db7_bb60_a9d5_23fc16890cf0 -->|calls| f50a836d_579d_7ed4_e51f_6bb4bd0b8059
  style d76c1f53_4db7_bb60_a9d5_23fc16890cf0 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/mrkl/base.py lines 188–216

    def from_chains(
        cls,
        llm: BaseLanguageModel,
        chains: list[ChainConfig],
        **kwargs: Any,
    ) -> AgentExecutor:
        """User-friendly way to initialize the MRKL chain.

        This is intended to be an easy way to get up and running with the
        MRKL chain.

        Args:
            llm: The LLM to use as the agent LLM.
            chains: The chains the MRKL system has access to.
            **kwargs: parameters to be passed to initialization.

        Returns:
            An initialized MRKL chain.
        """
        tools = [
            Tool(
                name=c.action_name,
                func=c.action,
                description=c.action_description,
            )
            for c in chains
        ]
        agent = ZeroShotAgent.from_llm_and_tools(llm, tools)
        return cls(agent=agent, tools=tools, **kwargs)