I have searched the existing issues and discussions.
Problem Description
It would be a nice feature to add top-k for Rag for Websearch so the total tokens parsed to my chat model are not that many and the performance doesnt degrade due to the large size of tokens. For example for SearXNG
By that i might me able to run lower context size for my models.
Desired Solution you'd like
Top-K limiting for Websearch
Alternatives Considered
No response
Additional Context
No response
Originally created by @Malte-Luehrs on GitHub (Oct 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18227
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
It would be a nice feature to add top-k for Rag for Websearch so the total tokens parsed to my chat model are not that many and the performance doesnt degrade due to the large size of tokens. For example for SearXNG
By that i might me able to run lower context size for my models.
### Desired Solution you'd like
Top-K limiting for Websearch
### Alternatives Considered
_No response_
### Additional Context
_No response_
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Malte-Luehrs on GitHub (Oct 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18227
Check Existing Issues
Problem Description
It would be a nice feature to add top-k for Rag for Websearch so the total tokens parsed to my chat model are not that many and the performance doesnt degrade due to the large size of tokens. For example for SearXNG
By that i might me able to run lower context size for my models.
Desired Solution you'd like
Top-K limiting for Websearch
Alternatives Considered
No response
Additional Context
No response