Bad request #655

rohpurohit · 2024-05-08T08:23:54Z

rohpurohit
May 8, 2024

I'm getting this error
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_KqmgeDw4EcFeJaxlINE4R0tr\", 'type': 'invalid_request_error', 'param': 'messages.[16].role', 'code': None}}

simple LLM call with gpt-3.5-turbo-0125 azure model, i'm using
azure client like

client = instructor.from_openai(azure_client)

        response, completion = client.chat.completions.create_with_completion(
            model=OPENAI_MODEL,
            messages=chat_history,
            temperature=OPENAI_TEMPERATURE,
            max_tokens=max_tokens,
            n=1,
            stop=None,
            response_model=model,
        )

the model is
class GenResponse(BaseModel): response: str req_assistance: bool objective: bool
and i'm not using function calling on my end, so it has to be from the library itself

rohpurohit · 2024-05-08T08:48:08Z

rohpurohit
May 8, 2024
Author

so i was doing two simultaneous LLM calls, and messages were same in both
and library was appending this
{'role': 'assistant', 'content': '', 'tool_calls': [{'id': 'call_TU4g0Kjwl6jCxR8rL3cgWCUe', 'function': {'arguments': 'response from the first call'] to the messages_object
that was the issue.

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

Bad request #655

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{editor}}'s edit

{{editor}}'s edit

Uh oh!

Replies: 1 comment

Uh oh!

{{title}}

Uh oh!

Select a reply

Uh oh!

Uh oh!

Bad request #655

Uh oh!

Uh oh!

rohpurohit May 8, 2024

Replies: 1 comment

Uh oh!

rohpurohit May 8, 2024 Author

rohpurohit
May 8, 2024

rohpurohit
May 8, 2024
Author