openai-python
openai-python copied to clipboard
openai
The official Python library for the OpenAI API
python gpt2.py Traceback (most recent call last): File "D:\EVE_NG\gpt2.py", line 2, in import openai File "D:\EVE_NG\openai.py", line 8, in response = openai.Completion.create( ^^^^^^^^^^^^^^^^^ AttributeError: partially initialized module 'openai' has no...
Fixes #98 Adds asyncio support for API. Does not support CLI (does not make sense). I haven't tested file upload. aiohttp does not include the files parameter like requests, so...
Exposing async interfaces would allow using this library in a much more modern, performant, and scalable way. Would be great if the maintainers could mention if they plan to add...
Request ID: .. Please contact us through our [help center](https://help.openai.com/en/) if this issue persists. Return to homepage
The library uses `requests` to fetch data from OpenAI servers, but we never call `.close()` on those connections which leaves dangling open file handles on the OS. Can we clean...
Hi, is there any way to reduce these logs? ``` message='OpenAI API response' path=https://api.openai.com/v1/fine-tunes processing_ms=228 request_id=FOO response_code=200 INFO:openai:message='OpenAI API response' path=https://api.openai.com/v1/fine-tunes processing_ms=228 request_id=BAR response_code=200 ``` To me, these logs should...
Hi, Is there a way to compute the number of tokens in the prompt before sending a request (in python)? I'd like to avoid the "too many tokens" error by...
I don't have access to the GPT-3 API yet (A guy can dream, eh?), but I have been reading through the docs and it seems like the completion module would...
Ubuntu 18.04.6 openai-python 0.23.1 python 3.8.13 I'm facing unexpected results when using `prompt_tokens` returned from the completion API in the davinci `codex` model. Consider the following function to reconstruct the...
