create_openai_tools_agent() — langchain Function Reference

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

Function python AgentOrchestration ClassicChains

Entity Profile

AgentOrchestration→ ClassicChains→ create_openai_tools_agent() — langchain Function Reference

Dependency Diagram

graph TD
  20b7be0c_4eb7_3a49_9552_06e511b3965c["create_openai_tools_agent()"]
  117d269f_041a_81c1_4599_9b3ce5564460["base.py"]
  20b7be0c_4eb7_3a49_9552_06e511b3965c -->|defined in| 117d269f_041a_81c1_4599_9b3ce5564460
  style 20b7be0c_4eb7_3a49_9552_06e511b3965c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/openai_tools/base.py lines 17–113

def create_openai_tools_agent(
    llm: BaseLanguageModel,
    tools: Sequence[BaseTool],
    prompt: ChatPromptTemplate,
    strict: bool | None = None,  # noqa: FBT001
) -> Runnable:
    """Create an agent that uses OpenAI tools.

    Args:
        llm: LLM to use as the agent.
        tools: Tools this agent has access to.
        prompt: The prompt to use. See Prompt section below for more on the expected
            input variables.
        strict: Whether strict mode should be used for OpenAI tools.

    Returns:
        A Runnable sequence representing an agent. It takes as input all the same input
        variables as the prompt passed in does. It returns as output either an
        AgentAction or AgentFinish.

    Raises:
        ValueError: If the prompt is missing required variables.

    Example:
        ```python
        from langchain_classic import hub
        from langchain_openai import ChatOpenAI
        from langchain_classic.agents import (
            AgentExecutor,
            create_openai_tools_agent,
        )

        prompt = hub.pull("hwchase17/openai-tools-agent")
        model = ChatOpenAI()
        tools = ...

        agent = create_openai_tools_agent(model, tools, prompt)
        agent_executor = AgentExecutor(agent=agent, tools=tools)

        agent_executor.invoke({"input": "hi"})

        # Using with chat history
        from langchain_core.messages import AIMessage, HumanMessage

        agent_executor.invoke(
            {
                "input": "what's my name?",
                "chat_history": [
                    HumanMessage(content="hi! my name is bob"),
                    AIMessage(content="Hello Bob! How can I assist you today?"),
                ],
            }
        )
        ```

    Prompt:

        The agent prompt must have an `agent_scratchpad` key that is a
            `MessagesPlaceholder`. Intermediate agent actions and tool output
            messages will be passed in here.

        Here's an example:

        ```python
        from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

        prompt = ChatPromptTemplate.from_messages(
            [
                ("system", "You are a helpful assistant"),
                MessagesPlaceholder("chat_history", optional=True),
                ("human", "{input}"),
                MessagesPlaceholder("agent_scratchpad"),
            ]
        )
        ```
    """
    missing_vars = {"agent_scratchpad"}.difference(
        prompt.input_variables + list(prompt.partial_variables),
    )
    if missing_vars:
        msg = f"Prompt missing required variables: {missing_vars}"