[PR #20020] [CLOSED] feat: use sigmoid function for reranking models to return scores from 0 to 1. #64286

New Issue

GiteaMirror · 2026-05-06T09:45:00-05:00

GiteaMirror commented

2026-05-06 09:45:00 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/20020
Author: @BarerRocket2678
Created: 12/17/2025
Status: ❌ Closed

Base: dev ← Head: retrieval-content-score-fix

📝 Commits (8)

fe6783c Merge pull request #19030 from open-webui/dev
fc05e0a Merge pull request #19405 from open-webui/dev
e3faec6 Merge pull request #19416 from open-webui/dev
9899293 Merge pull request #19448 from open-webui/dev
140605e Merge pull request #19462 from open-webui/dev
6f1486f Merge pull request #19466 from open-webui/dev
cfdf9bf Fixed retrieval.py to use sigmoid activation function
911e6c5 Update retrieval.py

📊 Changes

1 file changed (+4 additions, -1 deletions)

View changed files

📝 backend/open_webui/routers/retrieval.py (+4 -1)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request.

This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR.

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

Target branch: Verify that the pull request targets the dev branch. Not targeting the dev branch will lead to immediate closure of the PR.
Description: Provide a concise description of the changes made in this pull request down below.
Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
Documentation: If necessary, update relevant documentation Open WebUI Docs like environment variables, the tutorials, or other documentation sources.
Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Take this as an opportunity to make screenshots of the feature/fix and include it in the PR description.
Agentic AI Code: Confirm this Pull Request is not written by any AI Agent or has at least gone through additional human review AND manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR.
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?
Title 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 fix adds the torch.nn.Sigmoid() function to the sentence transformer reranking models. This makes all the cross encoder models return a value between 0 and 1 instead of around -10 to 10 as stated here:

You can initialize these models with activation_fn=torch.nn.Sigmoid() to force the model to return scores between 0 and 1. Otherwise, the raw value can reasonably range between -10 and 10.

Changed

Cross Encoder reranking models now return a value between 0 and 1.

Additional Information

Models Tested:
All tests were done by retrieving math information from a textbook in a knowledge database, the model in use was Qwen3 4B Instruct 2507.

cross-encoder/ms-marco-TinyBERT-L2-v2
cross-encoder/ms-marco-MiniLM-L2-v2
cross-encoder/ms-marco-MiniLM-L4-v2
cross-encoder/ms-marco-MiniLM-L6-v2
cross-encoder/ms-marco-MiniLM-L12-v2
cross-encoder/ms-marco-electra-base
BAAI/bge-reranker-v2-m3

Screenshots or Videos

Test example with cross-encoder/ms-marco-MiniLM-L6-v2 and Qwen3 4B Instruct 2507

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.

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

_{🔄 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/20020 **Author:** [@BarerRocket2678](https://github.com/BarerRocket2678) **Created:** 12/17/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `retrieval-content-score-fix` --- ### 📝 Commits (8) - [`fe6783c`](https://github.com/open-webui/open-webui/commit/fe6783c16699911c7be17392596d579333fb110c) Merge pull request #19030 from open-webui/dev - [`fc05e0a`](https://github.com/open-webui/open-webui/commit/fc05e0a6c5d39da60b603b4d520f800d6e36f748) Merge pull request #19405 from open-webui/dev - [`e3faec6`](https://github.com/open-webui/open-webui/commit/e3faec62c58e3a83d89aa3df539feacefa125e0c) Merge pull request #19416 from open-webui/dev - [`9899293`](https://github.com/open-webui/open-webui/commit/9899293f050ad50ae12024cbebee7e018acd851e) Merge pull request #19448 from open-webui/dev - [`140605e`](https://github.com/open-webui/open-webui/commit/140605e660b8186a7d5c79fb3be6ffb147a2f498) Merge pull request #19462 from open-webui/dev - [`6f1486f`](https://github.com/open-webui/open-webui/commit/6f1486ffd0cb288d0e21f41845361924e0d742b3) Merge pull request #19466 from open-webui/dev - [`cfdf9bf`](https://github.com/open-webui/open-webui/commit/cfdf9bf1213c34a610830a88f43d01d7a3a9cb14) Fixed retrieval.py to use sigmoid activation function - [`911e6c5`](https://github.com/open-webui/open-webui/commit/911e6c5bd652e09c8ab415c450c1aca7bcbdf9e6) Update retrieval.py ### 📊 Changes **1 file changed** (+4 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/routers/retrieval.py` (+4 -1) </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) to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request. This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR. **Before submitting, make sure you've checked the following:** - [X] **Target branch:** Verify that the pull request targets the `dev` branch. **Not targeting the `dev` branch will lead to immediate closure of the PR.** - [X] **Description:** Provide a concise description of the changes made in this pull request down below. - [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:** If necessary, update relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs) like environment variables, the tutorials, or other documentation sources. - [X] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [X] **Testing:** Perform manual tests to **verify the implemented fix/feature works as intended AND does not break any other functionality**. Take this as an opportunity to **make screenshots of the feature/fix and include it in the PR description**. - [X] **Agentic AI Code:** Confirm this Pull Request is **not written by any AI Agent** or has at least **gone through additional human review AND manual testing**. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR. - [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] **Title 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 fix adds the `torch.nn.Sigmoid()` function to the sentence transformer reranking models. This makes all the cross encoder models return a value between 0 and 1 instead of around -10 to 10 as stated [here:](https://www.sbert.net/docs/cross_encoder/pretrained_models.html) You can initialize these models with activation_fn=torch.nn.Sigmoid() to force the model to return scores between 0 and 1. Otherwise, the raw value can reasonably range between -10 and 10. ### Changed - Cross Encoder reranking models now return a value between 0 and 1. --- ### Additional Information Models Tested: All tests were done by retrieving math information from a textbook in a knowledge database, the model in use was Qwen3 4B Instruct 2507. - cross-encoder/ms-marco-TinyBERT-L2-v2 - cross-encoder/ms-marco-MiniLM-L2-v2 - cross-encoder/ms-marco-MiniLM-L4-v2 - cross-encoder/ms-marco-MiniLM-L6-v2 - cross-encoder/ms-marco-MiniLM-L12-v2 - cross-encoder/ms-marco-electra-base - BAAI/bge-reranker-v2-m3 ### Screenshots or Videos Test example with cross-encoder/ms-marco-MiniLM-L6-v2 and Qwen3 4B Instruct 2507 <img width="1111" height="520" alt="image" src="https://github.com/user-attachments/assets/ac05df2c-7fcb-416b-bb80-447f0da1fb7d" /> ### Contributor License Agreement By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. > [!NOTE] > Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in. --- <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 09:45:00 -05:00

GiteaMirror closed this issue

2026-05-06 09:45:04 -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#64286