dev branch: llama3 does not support tools? | Open Interpreter | Page 1

Hey folks,

Updated dev branch this morning. Is there change in flight with local/ollama support? I was able to get GUI mode working with gpt4-o, that's really cool. Trying to take it back local to see what I can do on-machine. I'm having trouble getting it going with ollama again, either gui mode or just regular. I'm getting grumbles of it not supporting tools. Tried both llama3 in regular mode and llama3.2-vision. Error looks like below -- anything I'm missing here? It seems to want to be told ollama as a provider, not be passed an api base now, so was playing with that a bit.

Thanks!

...
> Good morning

   Traceback (most recent call last):
  File "/home/doucej/miniconda3/envs/oi/lib/python3.11/site-packages/litellm/llms/openai/openai.py", line 692, in completion
    raise e
  File "/home/doucej/miniconda3/envs/oi/lib/python3.11/site-packages/litellm/llms/openai/openai.py", line 620, in completion
    self.make_sync_openai_chat_completion_request(
...
  File "/home/doucej/miniconda3/envs/oi/lib/python3.11/site-packages/openai/_base_client.py", line 1064, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'llama3 does not support tools', 'type': 'api_error', 'param': None, 'code': None}}

During handling of the above exception, another exception occurred:
...

#dev branch: llama3 does not support tools?