docs/how_to/agent_executor/

[giscus[bot]]

docs/how_to/agent_executor/

This section will cover building with the legacy LangChain AgentExecutor. These are fine for getting started, but past a certain point, you will likely want flexibility and control that they do not offer. For working with more advanced agents, we'd recommend checking out LangGraph Agents or the migration guide

https://python.langchain.com/docs/how_to/agent_executor/

[ajith-kumar-a]

model_with_tools = model.bind_tools(tools)
After binding tool i try to get response

response = model_with_tools.invoke([HumanMessage(content="Hi!")])

print(f"ContentString: {response.content}")

am getting the empyt content
not only for content="Hi!" it wont response anything why am facing this issue

[Marouansw]

brother , i'm facing the same issue, have you solved it?

[ryanma9629]

When creating_tool_calling_agent, we already have bound tools for this agent.
agent = create_tool_calling_agent(model, tools, prompt)

why do we need to bind them again when setting the agent executor?
agent_executor = AgentExecutor(agent=agent, tools=tools)

What will happen if we bind tools to the agent executor other than those when creating the agent?

[fzvincent]

the url "https://docs.smith.langchain.com/overview" is invalid, can you update it?