关于openAI 服务太慢的问题 Regarding the problem that openAI service is too slow
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
每次请求，/api/v1/chat/completions 接口 都会 重新获取 worker 的请求地址，我认为这是不必要的，只需要设置后台任务，不断的更新 worker 的请求地址。（每次都重新获取 worker 的请求地址，时间成本是巨大的。）
For every request, the /api/v1/chat/completions interface will re-obtain the worker's request address. I think this is unnecessary. You only need to set up background tasks to continuously update the worker's request address. (The time cost of re-obtaining the worker's request address every time is huge.)
Contributor guide
No contributing guide indexed for this repository
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 at the /api/v1/chat/completions entry point and trace where the worker request address is obtained for each request. Determine how that lookup can be refreshed in the background while preserving correct request routing; done means requests no longer repeat the costly lookup and worker addresses remain current.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100