deepset-ai / deepset-ai/haystack
Azure / OpenAI rate limit headers
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 26.6k
- Forks
- 3.2k
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 194
Description
Is your feature request related to a problem? Please describe.
Now OpenAIGenerator and OpenAIChatGenerator only returns choices without the response HTTP headers with rate limit information.
Describe the solution you'd like
Receive from OpenAIGenerator and OpenAIChatGenerator response headers or rate limit information.
Describe alternatives you've considered
Using OpenAI lib without Haystack
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
Locate the OpenAIGenerator and OpenAIChatGenerator entry points and inspect how their responses are currently returned. Determine how response headers or rate-limit information should be exposed for Azure/OpenAI requests, then add coverage for both generators showing that information is available to callers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- azure, python
- Domain
- api
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100