openai-python icon indicating copy to clipboard operation
openai-python copied to clipboard

The official Python library for the OpenAI API

Results 204 openai-python issues
Sort by recently updated
recently updated
newest added

### Describe the feature or improvement you're requesting Django bot chatgpt text not near, why? ![chatgpt](https://user-images.githubusercontent.com/39833970/222942356-741f98b4-aa65-44f9-8646-2b23dfc07bcd.PNG) chatgpt text near and space ![chatgpt2](https://user-images.githubusercontent.com/39833970/222942395-495fc103-e694-40f6-95b9-fb3e6d1f3134.PNG) ### Additional context _No response_

Modified command for installing dependencies to resolve the error message: 'no matches found: openai[embeddings]'

fix this issue:https://github.com/openai/openai-python/issues/243

### Describe the bug In an environment without direct access to the Internet, If you pass proxy settings to the `openai `object and try to perform input validation, the `openai.Moderation.create()`...

bug

### Describe the bug ![image](https://user-images.githubusercontent.com/61367724/223109301-718e8e33-36d8-4ad3-8146-f26eca0bc295.png) ![image](https://user-images.githubusercontent.com/61367724/223112509-f2a783fe-30bb-4402-849a-403cfbdb4697.png) when using async acreate , the API timeout ### To Reproduce async def chat(query, retry_count=0): response = await openai.ChatCompletion.acreate( model="gpt-3.5-turbo", messages=query, temperature=0.7, max_tokens=1200, top_p=1,...

bug

### Describe the feature or improvement you're requesting \openai\api_resources\abstract\engine_api_resource.py ```python result = _thread_context.session.request( method, abs_url, headers=headers, data=data, files=files, stream=stream, timeout=request_timeout if request_timeout else TIMEOUT_SECS, ) ``` add param ```python proxies=openai.proxy...

This ensures that the session is closed even if an exception is raised.

### Describe the bug use openai cli “chat_completions.create" failed to generate a response of sufficient length, and setting "--max-tokens" did not work. ### To Reproduce By default, the number of...

bug

### Describe the bug when calling `openai.ChatCompletion.create( model="gpt-3.5-turbo-0301", messages=[ { "role": "user", "content" : prompt } ], temperature=0.7, max_tokens=MAX_OUTPUT_BASE, n=1) ` multiple times in a loop I noticed that the...

bug