create_tool_calling_agent#

langchain.agents.tool_calling_agent.base.create_tool_calling_agent(llm: ~langchain_core.language_models.base.BaseLanguageModel, tools: ~typing.Sequence[~langchain_core.tools.base.BaseTool], prompt: ~langchain_core.prompts.chat.ChatPromptTemplate, *, message_formatter: ~typing.Callable[[~typing.Sequence[~typing.Tuple[~langchain_core.agents.AgentAction, str]]], ~typing.List[~langchain_core.messages.base.BaseMessage]] = <function format_to_tool_messages>) → Runnable[source]#

Create an agent that uses tools.

Parameters:

  • llm (BaseLanguageModel) – LLM to use as the agent.

  • tools (Sequence[BaseTool]) – Tools this agent has access to.

  • prompt (ChatPromptTemplate) – The prompt to use. See Prompt section below for more on the expected input variables.

  • message_formatter (Callable[[Sequence[Tuple[AgentAction, str]]], List[BaseMessage]]) – Formatter function to convert (AgentAction, tool output) tuples into FunctionMessages.

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.

Return type:

Runnable

Example

from langchain.agents import AgentExecutor, create_tool_calling_agent, tool
from langchain_anthropic import ChatAnthropic
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are a helpful assistant"),
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}"),
    ]
)
model = ChatAnthropic(model="claude-3-opus-20240229")

@tool
def magic_function(input: int) -> int:
    """Applies a magic function to an input."""
    return input + 2

tools = [magic_function]

agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

agent_executor.invoke({"input": "what is the value of magic_function(3)?"})

# 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.

Examples using create_tool_calling_agent

On this page