MaartenGr / MaartenGr/BERTopic
error : ServiceUnavailableError: The server is overloaded or not ready yet.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
Hello, I am experiencing a recurring issue with the `ServiceUnavailableError: The server is overloaded or not ready yet.` error while using chatgpt. Despite following the recommended guidelines and documentation, I am still encountering this problem. Here's how I implemented it in the code:
```
openai_model = OpenAI(model="gpt-3.5-turbo", exponential_backoff=True, chat=True
, delay_in_seconds=3, prompt=prompt)
```
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the OpenAI model construction shown in the issue and determine whether the error can be reproduced through BERTopic or comes from the external service. No repository file or test is identified, so completion would require a confirmed cause and either a supported fix or clear documentation of the limitation and workaround.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100