Groq provider broken

[ErikBjare]

openai.BadRequestError: Error code: 400 - {'error': {'message': "'messages.0' : for 'role:system' the following must be satisfied[('messages.0.content' : value must be a string)]", 'type': 'invalid_request_error'}}

[ErikBjare]

Fixed in 84c8316

[DrDavidL]

Still seeing same issue after installation:

[15:54:35] Browser tool available (using lynx)                                                                                                            
[15:54:39] Using model: groq/llama-3.3-70b-versatile                                                                                                          
[15:54:40] Using logdir ~/Library/Application Support/gptme/logs/2024-12-22-crawling-silly-robot                                                          
           Using workspace at ~                                                                                                                           
Skipped 1 hidden system messages, show with --show-hidden
--- ^^^ past messages ^^^ ---
User: hi
Traceback (most recent call last):                                                                                                                        
  File "/Users/david/.local/bin/gptme", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/click/core.py", line 1082, in main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/click/core.py", line 788, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/cli.py", line 282, in main
    chat(
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/chat.py", line 179, in chat
    for msg in step(
               ^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/chat.py", line 228, in step
    msg_response = reply(msgs, get_model().model, stream, tools)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/llm/__init__.py", line 57, in reply
    return _reply_stream(messages, model, tools)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/llm/__init__.py", line 102, in _reply_stream
    for char in (
                ^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/llm/__init__.py", line 103, in <genexpr>
    char for chunk in _stream(messages, model, tools) for char in chunk
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/gptme/llm/llm_openai.py", line 158, in stream
    for chunk_raw in openai.chat.completions.create(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/openai/_utils/_utils.py", line 275, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/openai/resources/chat/completions.py", line 859, in create
    return self._post(
           ^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/openai/_base_client.py", line 1280, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/openai/_base_client.py", line 957, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/david/Library/Application Support/pipx/venvs/gptme/lib/python3.12/site-packages/openai/_base_client.py", line 1061, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "'messages.0' : for 'role:system' the following must be satisfied[('messages.0.content' : value must be a string)]", 'type': 'invalid_request_error'}}