AgentExecutor is still necessary with create_react_agent ?

[mrctito]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

Its a conceitual question.

Description

@dosu,

Do I need to call AgentExecutor?

agent = create_react_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

Or not?

react_agent = create_react_agent(model=llm_with_tools, tools=tools, messages_modifier=prompt, checkpointer=memory)
inputs = {"messages": [HumanMessage(content=self.contexto["input"])]}
config={"configurable": {"thread_id": "1"}}
result = await react_agent.ainvoke(inputs, config=config, debug=True)

Thank you!

System Info

langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-experimental==0.0.62
langchain-openai==0.1.13
langchain-qdrant==0.1.0
langchain-text-splitters==0.2.1

[dosubot[bot]]

Yes, you need to call AgentExecutor when using create_react_agent.

Here's an example to illustrate this:

# Create the agent
memory = SqliteSaver.from_conn_string(":memory:")
model = ChatAnthropic(model_name="claude-3-sonnet-20240229")
search = TavilySearchResults(max_results=2)
tools = [search]
agent = create_react_agent(model, tools, checkpointer=memory)
agent_executor = AgentExecutor(agent=agent, tools=tools)

# Use the agent
config = {"configurable": {"thread_id": "abc123"}}
for chunk in agent_executor.stream(
    {"messages": [HumanMessage(content="hi im bob! and i live in sf")]}, config
):
    print(chunk)
    print("----")

for chunk in agent_executor.stream(
    {"messages": [HumanMessage(content="whats the weather where I live?")]}, config
):
    print(chunk)
    print("----")

In this code, agent is created using create_react_agent and then wrapped in AgentExecutor to stream messages ^[1][2].

Additionally, the LangChain documentation provides an example of using create_tool_calling_agent with AgentExecutor to interact with tools, which further supports the need to use AgentExecutor when working with agents created by functions like create_react_agent or create_tool_calling_agent ^[1][3][4].

To continue talking to Dosu, mention @dosu.