vanna-ai / vanna

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.
https://vanna.ai/docs/
MIT License
9.97k stars 737 forks source link

Fail to integration with llama.cpp #373

Closed njalan closed 3 months ago

njalan commented 3 months ago

I tried to set openai_api_base as the API started by llama.ccp OpenAI API compatible HTTP server. vanna is 4.0 and I got below error message: [2024-04-18 09:33:46,695] ERROR in app: Exception on /api/v0/generate_sql [GET] Traceback (most recent call last): File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/flask/app.py", line 1463, in wsgi_app response = self.full_dispatch_request() File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/flask/app.py", line 872, in full_dispatch_request rv = self.handle_user_exception(e) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/flask/app.py", line 870, in full_dispatch_request rv = self.dispatch_request() File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/flask/app.py", line 855, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(view_args) # type: ignore[no-any-return] File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/vanna/flask/init.py", line 130, in decorated return f(args, user=user, kwargs) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/vanna/flask/init.py", line 307, in generate_sql sql = vn.generate_sql(question=question) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/vanna/base/base.py", line 122, in generate_sql llm_response = self.submit_prompt(prompt, kwargs) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/vanna/openai/openai_chat.py", line 123, in submit_prompt response = self.client.chat.completions.create( File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/openai/_utils/_utils.py", line 275, in wrapper return func(args, kwargs) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/openai/resources/chat/completions.py", line 667, in create return self._post( File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/openai/_base_client.py", line 1213, in post return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)) File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/openai/_base_client.py", line 902, in request return self._request( File "/home/hadoop/.conda/envs/vanna2/lib/python3.9/site-packages/openai/_base_client.py", line 993, in _request raise self._make_status_error_from_response(err.response) from None openai.NotFoundError: Error code: 404 - {'error': {'code': 404, 'message': 'File Not Found', 'type': 'not_found_error'}}

zainhoda commented 3 months ago

This is a 404 error that originates from within the openaipackage. You should first verify that you're able to use the OpenAI client directly to perform chat.completions.create