When I use the tool in Agent, it returns OPEN AI 400 Bad Request.

[reinershir]

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

from langchain_community.utilities import SerpAPIWrapper
        from langchain.agents import create_openai_tools_agent
        from langchain.agents import AgentExecutor,Tool

        chat = ChatOpenAI(model="gpt-3.5-turbo-1106",streaming=True)

        search = SerpAPIWrapper()
        #search = GoogleSearchAPIWrapper()
        
        tools = [Tool(
            name="google_search",
            description="Search Google for recent results.",
            func=search.run,
            return_direct=False
        )]

        prompt = ChatPromptTemplate.from_messages(
            [
                (
                    "system",
                    "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!",
                ),
                MessagesPlaceholder(variable_name="messages"),
                MessagesPlaceholder(variable_name="agent_scratchpad"),
            ]
        )
        agent = create_openai_tools_agent(tools = tools,llm = chat,prompt=prompt)
        agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
        

        for chunk in agent_executor.stream({"messages": chat_history.messages}):
                for key in chunk:
                    if key not in output:
                        output[key] = chunk[key]
                    else:
                        output[key] += chunk[key]
                if "actions" in chunk:
                    for action in chunk["actions"]:
                        print(f"Calling Tool: `{action.tool}` with input `{action.tool_input}`")
                    continue
                if "steps" in chunk:
                    observation = chunk["steps"][-1].observation
                    for step in chunk["steps"]:
                        print(f"Tool Result: `{step.observation}`")
                    continue

                if "output" in chunk:
                     print(chunk["output"], end="", flush=True)
                     response_json =  json.dumps({"stat": "SUCCESS", "content": chunk["output"]})

Description

I want to integrate Google search into my chatbot and use streaming output. It returned the following error: openai.BadRequestError: Error code: 400.

I searched on both Google and Github but did not find any relevant information.

The complete return information is:

{'error': {'message': "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_APhVboGGQV2ZfLqDnqukNltV", 'type': 'invalid_request_error', 'param': 'messages.[4].role', 'code': None}}

System Info

System Information

OS: Windows
OS Version: 10.0.19045
Python Version: 3.12.1 (tags/v3.12.1:2305ca5, Dec 7 2023, 22:03:25) [MSC v.1937 64 bit (AMD64)]

Package Information

langchain_core: 0.1.32
langchain: 0.1.12
langchain_community: 0.0.28
langsmith: 0.1.27
langchain_openai: 0.0.8
langchain_text_splitters: 0.0.1
langchainhub: 0.1.15

[dosubot[bot]]

The error you're encountering, BadRequestError: Error code: 400, is likely due to a mismatch or absence of responses for tool calls made during the conversation. When using LangChain to make tool calls, each call must be followed by a corresponding tool message that responds to the tool_call_id. The error message indicates that there was at least one tool call (call_APhVboGGQV2ZfLqDnqukNltV) that did not have a matching tool message response.

To resolve this issue, ensure that for every ToolCall made, there is a corresponding ToolMessage with a tool_call_id that matches the id of the ToolCall. This is crucial for the LangChain library to correctly process the conversation flow and associate tool responses with their respective calls.

Here's a quick example to illustrate how to format a tool call and its response correctly:

msgs: List = [
    HumanMessage("Example question?"),
    AIMessage(
        content="",
        tool_calls=[
            ToolCall(
                name="ExampleTool",
                args={"key": "value"},
                id="unique_id",
            )
        ],
    ),
    ToolMessage("Example response", tool_call_id="unique_id"),
]

In this example, a ToolCall is made with an id of "unique_id", and a corresponding ToolMessage is provided with a tool_call_id that matches the id of the ToolCall, ensuring the response is correctly associated with the call.

Make sure to implement logic that tracks these IDs and correctly associates responses with their calls, especially if you're dynamically generating tool calls and responses. This should help in resolving the BadRequestError you're facing.

Sources

• Error Code 400. Can ask follow up questions with agent_executor
• libs/partners/openai/tests/integration_tests/chat_models/test_base.py
• libs/langchain/langchain/agents/agent.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[thewoowon]

First case. no Runnable -> it's working well

llm = ChatOpenAI(
    model="gpt-4o",
    openai_api_key=API_KEY
)

tools = [get_table_info]

llm_with_tools = llm.bind_tools(tools)

# ... syncopation

# messages -> human, ai, tool -> perfect object

llm_with_tools.invoke(messages)

# no Runnable

Second case. Wrapping Runnable, It's not working...

llm = ChatOpenAI(
    model="gpt-4o",
    openai_api_key=API_KEY
)

tools = [get_table_info]

llm_with_tools = llm.bind_tools(tools)

chain = RunnableWithMessageHistory(llm_with_tools, get_session_history)

# ... syncopation

# messages -> human, ai, tool -> perfect object

chain .invoke(messages)

BadRequestError: Error code: 400 - {'error': {'message': "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_V4oO156xtOC6a0RXllhfH3n6", 'type': 'invalid_request_error', 'param': 'messages.[2].role', 'code': None}}

Please let me know...help me

[progpyftk]

Any update on it?

[arkodeep3404]

any solution???

[renatosaz]

Any update?

[arkodeep3404]

nah bro
seems to be completely ignored