[PR #14255] [CLOSED] feat: Enhance RAG context with detailed source attributes #62280

New Issue

GiteaMirror · 2026-05-06T06:20:09-05:00

GiteaMirror commented

2026-05-06 06:20:09 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/14255
Author: @decent-engineer-decent-datascientist
Created: 5/23/2025
Status: ❌ Closed

Base: dev ← Head: dev

📝 Commits (1)

721d9f0 Enhance RAG context with detailed source attributes

📊 Changes

1 file changed (+35 additions, -12 deletions)

View changed files

📝 backend/open_webui/utils/middleware.py (+35 -12)

📄 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 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 pull request enhances the RAG (Retrieval Augmented Generation) context string generated in middleware.py. The motivation is to provide richer, more structured metadata to the language model by adding descriptive attributes to the <source> tags. Specifically, it introduces name (for the display name of the file/tool) and source_identifier (for the specific underlying source string or ID) alongside the existing numeric id. This change aims to improve the LLM's ability to comprehend and accurately cite the sources of its information.

Added

New attributes name and source_identifier to the <source> tags within the RAG context_string generated in middleware.py.
- The name attribute stores the human-readable display name of the parent file or tool (e.g., "annual_report.pdf").
- The source_identifier attribute stores the specific string used to identify the source of the content (e.g., filename from metadata, file ID, tool name).

Changed

Modified the logic in the process_chat_payload function within middleware.py to construct the RAG context_string to include the new name and source_identifier attributes in each <source> tag, alongside the existing id attribute.

Deprecated

N/A

Removed

N/A

Fixed

N/A

Security

N/A

Breaking Changes

N/A (This is an additive change to the internal structure of the RAG context string. While LLM processing of this string might change, it's not expected to break API contracts or other system components.)

Additional Information

This change builds upon the existing RAG context generation mechanism by making the source metadata more explicit and structured within the <source> tags.
The goal is to allow the LLM to potentially make more informed use of the provided context and improve the clarity of source attribution in its responses.
Related discussion: https://github.com/open-webui/open-webui/discussions/11775

Screenshots or Videos

N/A (Code change, visual output is indirect via LLM responses)

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/14255 **Author:** [@decent-engineer-decent-datascientist](https://github.com/decent-engineer-decent-datascientist) **Created:** 5/23/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `dev` --- ### 📝 Commits (1) - [`721d9f0`](https://github.com/open-webui/open-webui/commit/721d9f0d9d6577252dac89550d62bf20771c55c2) Enhance RAG context with detailed source attributes ### 📊 Changes **1 file changed** (+35 additions, -12 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/utils/middleware.py` (+35 -12) </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? - [ ] **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? - [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 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 pull request enhances the RAG (Retrieval Augmented Generation) context string generated in `middleware.py`. The motivation is to provide richer, more structured metadata to the language model by adding descriptive attributes to the `<source>` tags. Specifically, it introduces `name` (for the display name of the file/tool) and `source_identifier` (for the specific underlying source string or ID) alongside the existing numeric `id`. This change aims to improve the LLM's ability to comprehend and accurately cite the sources of its information. ### Added - New attributes `name` and `source_identifier` to the `<source>` tags within the RAG `context_string` generated in `middleware.py`. - The `name` attribute stores the human-readable display name of the parent file or tool (e.g., "annual_report.pdf"). - The `source_identifier` attribute stores the specific string used to identify the source of the content (e.g., filename from metadata, file ID, tool name). ### Changed - Modified the logic in the `process_chat_payload` function within `middleware.py` to construct the RAG `context_string` to include the new `name` and `source_identifier` attributes in each `<source>` tag, alongside the existing `id` attribute. ### Deprecated - N/A ### Removed - N/A ### Fixed - N/A ### Security - N/A ### Breaking Changes - N/A (This is an additive change to the internal structure of the RAG context string. While LLM processing of this string might change, it's not expected to break API contracts or other system components.) --- ### Additional Information - This change builds upon the existing RAG context generation mechanism by making the source metadata more explicit and structured within the `<source>` tags. - The goal is to allow the LLM to potentially make more informed use of the provided context and improve the clarity of source attribution in its responses. - Related discussion: https://github.com/open-webui/open-webui/discussions/11775 ### Screenshots or Videos - N/A (Code change, visual output is indirect via LLM responses) ### 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 2026-05-06 06:20:09 -05:00

GiteaMirror closed this issue

2026-05-06 06:20:13 -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#62280