[PR #11497] [MERGED] feat: Added new k_reranker parameter #61603

New Issue

GiteaMirror · 2026-05-06T05:08:09-05:00

GiteaMirror commented

2026-05-06 05:08:09 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/11497
Author: @mahenning
Created: 3/10/2025
Status: ✅ Merged
Merged: 3/27/2025
Merged by: @tjbck

Base: dev ← Head: k_reranker

📝 Commits (8)

41a4cf7 Added new k_reranker parameter
8b5b3f1 Add translation (partially)
c877b59 Address edge case with k < k_reranker, sort results for cutting off
f13948d Fixed typo
ba676b7 Use k_reranker also for result merge, and add special sorting use case for ChromaDB
5ab789e Add documentation on chroma special case
5f48af5 Revert the ordering change with chromadb, not necessary with reranker results
9d834a8 Merge branch 'dev' into k_reranker

📊 Changes

9 files changed (+57 additions, -5 deletions)

View changed files

📝 backend/open_webui/config.py (+5 -0)
📝 backend/open_webui/main.py (+2 -0)
📝 backend/open_webui/retrieval/utils.py (+20 -5)
📝 backend/open_webui/routers/retrieval.py (+8 -0)
📝 backend/open_webui/utils/middleware.py (+1 -0)
📝 src/lib/components/admin/Settings/Documents.svelte (+18 -0)
📝 src/lib/i18n/locales/de-DE/translation.json (+1 -0)
📝 src/lib/i18n/locales/en-GB/translation.json (+1 -0)
📝 src/lib/i18n/locales/en-US/translation.json (+1 -0)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

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 for validating 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 cleary 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

Adds a separate top k value for the reranker, making the RAG pipeline more flexible

Added

Adds a separate top k value for the reranker that can be set in the documents tab in admin settings

Additional Information

Example: Retrieve top_k=100 results from the embedding space, then rerank them and give the top_k_reranker=20 document chunks to the LLM. Right now you have to decide to set top k high and clutter the LLM context indow, or use a low top k i embedding space. Embedding
I know that the Minimum Score parameter already exists, but in my tests I didn't find a value that reliably works. Some queries hit 0.9 similarity score (especially if some document-related key words are in the query). Sometimes the similarity was only 0.01, but still with relevant information, which would be filtered out by a fixed threshold value.
The top_k_reranker parameter is hidden in the UI if hybrid search is disabled, the same way the reranker model field works. This PR also don't break stuff for users who don't want to use two different top_k. Just set both to the same value to get the current behavior.

_{🔄 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/11497 **Author:** [@mahenning](https://github.com/mahenning) **Created:** 3/10/2025 **Status:** ✅ Merged **Merged:** 3/27/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `k_reranker` --- ### 📝 Commits (8) - [`41a4cf7`](https://github.com/open-webui/open-webui/commit/41a4cf7106639b46b68a3ef4117129e14b54c633) Added new k_reranker parameter - [`8b5b3f1`](https://github.com/open-webui/open-webui/commit/8b5b3f165adc22050d2f8c86cd6f172f0c7eda06) Add translation (partially) - [`c877b59`](https://github.com/open-webui/open-webui/commit/c877b59cbcf6e6c141be2241201b7726e5f78af9) Address edge case with k < k_reranker, sort results for cutting off - [`f13948d`](https://github.com/open-webui/open-webui/commit/f13948d805c973194955bb043ffbd306472edc63) Fixed typo - [`ba676b7`](https://github.com/open-webui/open-webui/commit/ba676b7ed6a4ce141474d7c31797ea2fd8aa513a) Use k_reranker also for result merge, and add special sorting use case for ChromaDB - [`5ab789e`](https://github.com/open-webui/open-webui/commit/5ab789e83e124af5383a06a80dd3e55cef713f2b) Add documentation on chroma special case - [`5f48af5`](https://github.com/open-webui/open-webui/commit/5f48af5b9114d480d7c9bea71c298f1fde001563) Revert the ordering change with chromadb, not necessary with reranker results - [`9d834a8`](https://github.com/open-webui/open-webui/commit/9d834a8e90467edd574f18fbbe685df63731c610) Merge branch 'dev' into k_reranker ### 📊 Changes **9 files changed** (+57 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+5 -0) 📝 `backend/open_webui/main.py` (+2 -0) 📝 `backend/open_webui/retrieval/utils.py` (+20 -5) 📝 `backend/open_webui/routers/retrieval.py` (+8 -0) 📝 `backend/open_webui/utils/middleware.py` (+1 -0) 📝 `src/lib/components/admin/Settings/Documents.svelte` (+18 -0) 📝 `src/lib/i18n/locales/de-DE/translation.json` (+1 -0) 📝 `src/lib/i18n/locales/en-GB/translation.json` (+1 -0) 📝 `src/lib/i18n/locales/en-US/translation.json` (+1 -0) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) and describe your changes before submitting a pull request. **Before submitting, make sure you've checked the following:** - [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. - [x] **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? - [x] **Testing:** Have you written and run sufficient tests for validating the changes? - [x] **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 cleary 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 - Adds a separate top k value for the reranker, making the RAG pipeline more flexible ### Added - Adds a separate top k value for the reranker that can be set in the documents tab in admin settings --- ### Additional Information - Example: Retrieve `top_k=100` results from the embedding space, then rerank them and give the `top_k_reranker=20` document chunks to the LLM. Right now you have to decide to set top k high and clutter the LLM context indow, or use a low top k i embedding space. Embedding - I know that the Minimum Score parameter already exists, but in my tests I didn't find a value that reliably works. Some queries hit 0.9 similarity score (especially if some document-related key words are in the query). Sometimes the similarity was only 0.01, but still with relevant information, which would be filtered out by a fixed threshold value. - The top_k_reranker parameter is hidden in the UI if hybrid search is disabled, the same way the reranker model field works. This PR also don't break stuff for users who don't want to use two different top_k. Just set both to the same value to get the current behavior. --- <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 2026-05-06 05:08:09 -05:00

GiteaMirror closed this issue

2026-05-06 05:08:11 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#61603