I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.
Verify Feature Scope
I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.
Problem Description
Currently, Open WebUI allows the configuration and use of reranking models within the internal RAG. However, unlike embeddings and chat completions, there is no public API endpoint to access the configured reranker externally. While the model appears in the model list, it cannot be called through Open WebUI API.
Desired Solution you'd like
I would like to see a dedicated API endpoint (e.g., /v1/rerank or /api/rerank) that follows the de facto industry standard used by Cohere, vLLM etc. This would allow external tools and scripts to utilize the reranking models already configured in Open WebUI.
A similar gap was previously addressed for the embedding API (see #8719), and adding reranking support would improve the feature set for using Open WebUI as a unified model provider.
Alternatives Considered
Currently, the only way to use reranking is to proxy the API endpoint directly to the backend, bypassing Open WebUI.
Additional Context
No response
Originally created by @JKratto on GitHub (Mar 15, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22698
### Check Existing Issues
- [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request.
### Verify Feature Scope
- [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.
### Problem Description
Currently, Open WebUI allows the configuration and use of reranking models within the internal RAG. However, unlike embeddings and chat completions, there is no public API endpoint to access the configured reranker externally. While the model appears in the model list, it cannot be called through Open WebUI API.
### Desired Solution you'd like
I would like to see a dedicated API endpoint (e.g., /v1/rerank or /api/rerank) that follows the de facto industry standard used by Cohere, vLLM etc. This would allow external tools and scripts to utilize the reranking models already configured in Open WebUI.
A similar gap was previously addressed for the embedding API (see #8719), and adding reranking support would improve the feature set for using Open WebUI as a unified model provider.
### Alternatives Considered
Currently, the only way to use reranking is to proxy the API endpoint directly to the backend, bypassing Open WebUI.
### 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 @JKratto on GitHub (Mar 15, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22698
Check Existing Issues
Verify Feature Scope
Problem Description
Currently, Open WebUI allows the configuration and use of reranking models within the internal RAG. However, unlike embeddings and chat completions, there is no public API endpoint to access the configured reranker externally. While the model appears in the model list, it cannot be called through Open WebUI API.
Desired Solution you'd like
I would like to see a dedicated API endpoint (e.g., /v1/rerank or /api/rerank) that follows the de facto industry standard used by Cohere, vLLM etc. This would allow external tools and scripts to utilize the reranking models already configured in Open WebUI.
A similar gap was previously addressed for the embedding API (see #8719), and adding reranking support would improve the feature set for using Open WebUI as a unified model provider.
Alternatives Considered
Currently, the only way to use reranking is to proxy the API endpoint directly to the backend, bypassing Open WebUI.
Additional Context
No response