search

MervinPraison / PraisonAI

PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.
https://docs.praison.ai
MIT License
1.26k stars 188 forks source link

Problem running 'praisonai --init create a movie script about dog in moon ' #4

Closed joliva closed 3 months ago

joliva commented 3 months ago

pip install praisonai

Environment: MacOS Sonoma Python 3.11 Ollama server running OPENAI_API_KEY=fake OPENAI_API_BASE=http://localhost:11434/api/generate OPENAI_MODEL_NAME=mistral

Run Output:

Traceback (most recent call last): File "/Users/joliva/.pyenv/versions/3.11.6/bin/praisonai", line 8, in sys.exit(main()) ^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/main.py", line 7, in main praison_ai.main() File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/cli.py", line 154, in main self.agent_file = generator.generate() ^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/praisonai/auto.py", line 44, in generate response = self.client.chat.completions.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 570, in new_create_sync response = retry_sync( ^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 387, in retry_sync for attempt in max_retries: File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 347, in iter do = self.iter(retry_state=retry_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 325, in iter raise retry_exc.reraise() ^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/tenacity/init.py", line 158, in reraise raise self.last_attempt.result() ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.get_result() ^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/concurrent/futures/_base.py", line 401, in get_result raise self._exception File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/instructor/patch.py", line 390, in retry_sync response = func(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_utils/_utils.py", line 275, in wrapper return func(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 667, in create return self._post( ^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 1208, in post return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 897, in request return self._request( ^^^^^^^^^^^^^^ File "/Users/joliva/.pyenv/versions/3.11.6/lib/python3.11/site-packages/openai/_base_client.py", line 988, in _request raise self._make_status_error_from_response(err.response) from None openai.NotFoundError: 404 page not found

franciscoabenza commented 3 months ago

what version of openai are you using? openai -V

jyonny-byte commented 3 months ago

You need to use OPENAI_API_BASE=http://localhost:11434/v1

Not /api/generate when making openai structure calls

joliva commented 3 months ago

OPENAI_API_BASE=http://localhost:11434/v1

That was the ticket - thanks!