o Jjg @sddlmZmZmZmZddlmZddlmZddl m Z ddl m Z ddl mZmZddlmZddlmZdd lmZeeeeefgee fZed d ed eed e dedef ddZdS))CallableListSequenceTuple) AgentAction)BaseLanguageModel) BaseMessage)ChatPromptTemplate)RunnableRunnablePassthrough)BaseTool)format_to_tool_messages)ToolsAgentOutputParsermessage_formatterllmtoolspromptrreturncsldh|jt|j}|rtd|t|dstd||}tjfddd|B|Bt B}|S)a. Create an agent that uses 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. message_formatter: 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. Example: .. code-block:: python 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. agent_scratchpadz#Prompt missing required variables: bind_toolszFThis function requires a .bind_tools method be implemented on the LLM.cs |dS)Nintermediate_steps)xrr`/var/www/html/zoom/venv/lib/python3.10/site-packages/langchain/agents/tool_calling_agent/base.pyfs z+create_tool_calling_agent..)r) differenceinput_variableslistpartial_variables ValueErrorhasattrrr assignr)rrrr missing_varsllm_with_toolsagentrrrcreate_tool_calling_agents*F   r&N)typingrrrrlangchain_core.agentsrlangchain_core.language_modelsrlangchain_core.messagesrlangchain_core.prompts.chatr langchain_core.runnablesr r langchain_core.toolsr (langchain.agents.format_scratchpad.toolsr %langchain.agents.output_parsers.toolsrstrMessageFormatterr&rrrrs,