[PR #13745] [CLOSED] feat: add API-based reranker support for RAG #38907

Closed
opened 2026-04-25 11:42:43 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/13745
Author: @jescalada
Created: 5/10/2025
Status: Closed

Base: devHead: add-remote-reranker


📝 Commits (4)

  • a3bb7df Merge pull request #13530 from open-webui/dev
  • fa88849 feat: extend RerankCompressor for remote rerank API config
  • bada2c0 feat: add rerank_remote function to handle reranker API calls
  • c10b0af fix: reranker scores.tolist error

📊 Changes

1 file changed (+106 additions, -13 deletions)

View changed files

📝 backend/open_webui/retrieval/utils.py (+106 -13)

📄 Description

Fixes #8478.

I did manual testing for a few flows, however no unit tests:

  1. API-based reranking
  2. Missing API parameters
    -> Uses regular hybrid search instead
  3. API errors out
    -> Uses regular hybrid search instead

Let me know if more thorough testing is needed! I'm happy to write unit tests if I can get some pointers on how to test the RAG flow.

Thank you!

Pull Request Checklist

  • Target branch: Please verify that the pull request targets the dev branch.
  • Description: Provide a concise description of the changes made in this pull request.
  • Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
  • Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
  • Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
  • Testing: Have you written and run sufficient tests to validate the changes?
  • Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
  • Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
    • BREAKING CHANGE: Significant changes that may affect compatibility
    • build: Changes that affect the build system or external dependencies
    • ci: Changes to our continuous integration processes or workflows
    • chore: Refactor, cleanup, or other non-functional code changes
    • docs: Documentation update or addition
    • feat: Introduces a new feature or enhancement to the codebase
    • fix: Bug fix or error correction
    • i18n: Internationalization or localization changes
    • perf: Performance improvement
    • refactor: Code restructuring for better maintainability, readability, or scalability
    • style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
    • test: Adding missing tests or correcting existing tests
    • WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

This PR adds remote reranking capabilities to the RAG system. It is activated by providing REMOTE_RERANKER_URL, REMOTE_RERANKER_KEY and REMOTE_RERANKER_MODEL environment variables, and setting the query mode to "hybrid" on the UI settings Settings > Documents > Retrieval > Hybrid Search.

Added

  • Add remote_reranker function for handling calls to a remote reranking API

Changed

  • Refactor RerankCompressor to handle multiple scenarios more cleanly (API reranking, local reranking via reranking and embedding functions)
    • Added error handling

Deprecated

None

Removed

None

Fixed

None

Security

None

Breaking Changes

None


Additional Information

This is a highly-requested feature: #8478

I implemented this by using some of the suggested code in the issue and then simplifying and refactoring to get a working flow. Let me know if anything requires further refactoring or testing! 😃

Screenshots or Videos

Remote reranker in action (Jina)

image

Local hybrid reranker

This is the default flow when the API config envs are missing or the API request failed (same as before):

image

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/13745 **Author:** [@jescalada](https://github.com/jescalada) **Created:** 5/10/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `add-remote-reranker` --- ### 📝 Commits (4) - [`a3bb7df`](https://github.com/open-webui/open-webui/commit/a3bb7df61058e690a76cebb7681bd5390e77d226) Merge pull request #13530 from open-webui/dev - [`fa88849`](https://github.com/open-webui/open-webui/commit/fa88849c95ed5146a530da22ab628560ec94b8ac) feat: extend RerankCompressor for remote rerank API config - [`bada2c0`](https://github.com/open-webui/open-webui/commit/bada2c08d89f1df9fa9fe72273fd1663b63a8be5) feat: add rerank_remote function to handle reranker API calls - [`c10b0af`](https://github.com/open-webui/open-webui/commit/c10b0af8013d0f42bce33c9f901c998dd0122027) fix: reranker scores.tolist error ### 📊 Changes **1 file changed** (+106 additions, -13 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/retrieval/utils.py` (+106 -13) </details> ### 📄 Description Fixes #8478. I did manual testing for a few flows, however no unit tests: 1. API-based reranking 2. Missing API parameters -> Uses regular hybrid search instead 3. API errors out -> Uses regular hybrid search instead Let me know if more thorough testing is needed! I'm happy to write unit tests if I can get some pointers on how to test the RAG flow. Thank you! # Pull Request Checklist - [x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [x] **Description:** Provide a concise description of the changes made in this pull request. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [ ] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources? - [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [ ] **Testing:** Have you written and run sufficient tests to validate the changes? - [ ] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description This PR adds remote reranking capabilities to the RAG system. It is activated by providing `REMOTE_RERANKER_URL`, `REMOTE_RERANKER_KEY` and `REMOTE_RERANKER_MODEL` environment variables, and setting the query mode to "hybrid" on the UI settings `Settings > Documents > Retrieval > Hybrid Search`. ### Added - Add `remote_reranker` function for handling calls to a remote reranking API ### Changed - Refactor `RerankCompressor` to handle multiple scenarios more cleanly (API reranking, local reranking via reranking and embedding functions) - Added error handling ### Deprecated None ### Removed None ### Fixed None ### Security None ### Breaking Changes None --- ### Additional Information This is a highly-requested feature: #8478 I implemented this by using some of the suggested code in the issue and then simplifying and refactoring to get a working flow. Let me know if anything requires further refactoring or testing! 😃 ### Screenshots or Videos #### Remote reranker in action (Jina) ![image](https://github.com/user-attachments/assets/0e38238c-2740-42b8-908c-43d32da455ee) #### Local hybrid reranker This is the default flow when the API config envs are missing or the API request failed (same as before): ![image](https://github.com/user-attachments/assets/dfb11b75-b319-4a71-b719-bf68fe2db8ef) ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-25 11:42:43 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#38907