[PR #24213] fix: handle file-only chat messages with full context #50554

New Issue

GiteaMirror · 2026-04-30T03:19:58-05:00

GiteaMirror commented

2026-04-30 03:19:58 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/24213
Author: @ShrootBuck
Created: 4/29/2026
Status: 🔄 Open

Base: dev ← Head: main

📝 Commits (1)

1d83c9b Treat file-only uploads as full context

📊 Changes

1 file changed (+19 additions, -7 deletions)

View changed files

📝 backend/open_webui/utils/middleware.py (+19 -7)

📄 Description

Pull Request Checklist

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

Target branch: Verify that the pull request targets the dev branch. PRs targeting main will be immediately closed.
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: Add docs in Open WebUI Docs Repository. Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps.
Dependencies: Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash.
Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to make screenshots of the feature/fix and include them 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?
Design & Architecture: Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes.
Git Hygiene: Keep PRs atomic (one logical change). Clean up commits and rebase on dev to ensure no unrelated commits (e.g. from main) are included. Push updates to the existing PR branch instead of closing and reopening.
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

Fixes file-only chat messages where a user uploads/attaches a document but sends no text prompt. Previously, the backend could successfully collect file sources, including full-context sources, but skip injecting them into the model prompt because the user prompt was empty. This caused models to respond as if they were only waiting for instructions.

Added

No new user-facing settings or dependencies.

Changed

File context handling now skips retrieval query generation when the latest user message is empty (cause the whole point of RAG is a vector query...)
File-only messages are treated as full-context attachment turns, so the model receives the attached document context instead of attempting query-based retrieval without a query.
Source context injection now uses an internal effective prompt when the user message is empty but file sources are available.

Deprecated

None.

Removed

None.

Fixed

Fixed empty-prompt file uploads not injecting collected file context into the model message.
Fixed query-based RAG running with an empty prompt for file-only turns.
Fixed native tool citation context rebuilding to use the preserved original/effective user prompt instead of a potentially already-templated RAG message.

Security

None.

Breaking Changes

None.

Additional Information

Query-based RAG requires a meaningful user query. When the user attaches a file without typing a prompt, there is no reliable query to use for semantic retrieval. In that case, using the existing full-context path is more deterministic and matches the user's implicit intent: use the attached document in the current conversation.
This preserves the existing query-based RAG behavior when the user does provide a prompt.
This reuses the existing full-context file handling path rather than adding a new setting.

Testing

Manual reproduction before the fix:
- Attach/upload a document.
- Send the message with no typed prompt.
- The model responds as if no task/context was provided, such as saying it is ready for instructions.
Expected behavior after the fix:
- Attach/upload a document.
- Send the message with no typed prompt.
- The backend treats the turn as full-context file usage and injects the file context with an internal effective prompt, allowing the model to respond based on the attached document and conversation context.

Screenshots or Videos

Not included. This is a backend chat payload/context handling fix.

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/24213 **Author:** [@ShrootBuck](https://github.com/ShrootBuck) **Created:** 4/29/2026 **Status:** 🔄 Open **Base:** `dev` ← **Head:** `main` --- ### 📝 Commits (1) - [`1d83c9b`](https://github.com/open-webui/open-webui/commit/1d83c9b55d4936d2260bbd3505fe8c028eb33852) Treat file-only uploads as full context ### 📊 Changes **1 file changed** (+19 additions, -7 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/utils/middleware.py` (+19 -7) </details> ### 📄 Description  # Pull Request Checklist  **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Verify that the pull request targets the `dev` branch. **PRs targeting `main` will be immediately closed.** - [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. - [ ] **Documentation:** Add docs in [Open WebUI Docs Repository](https://github.com/open-webui/docs). Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps. - [ ] **Dependencies:** Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash. - [x] **Testing:** Perform manual tests to **verify the implemented fix/feature works as intended AND does not break any other functionality**. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to **make screenshots of the feature/fix and include them 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] **Design & Architecture:** Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes. - [x] **Git Hygiene:** Keep PRs atomic (one logical change). Clean up commits and rebase on `dev` to ensure no unrelated commits (e.g. from `main`) are included. Push updates to the existing PR branch instead of closing and reopening. - [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 - Fixes file-only chat messages where a user uploads/attaches a document but sends no text prompt. Previously, the backend could successfully collect file sources, including full-context sources, but skip injecting them into the model prompt because the user prompt was empty. This caused models to respond as if they were only waiting for instructions. ### Added - No new user-facing settings or dependencies. ### Changed - File context handling now skips retrieval query generation when the latest user message is empty (cause the whole point of RAG is a vector _query_...) - File-only messages are treated as full-context attachment turns, so the model receives the attached document context instead of attempting query-based retrieval without a query. - Source context injection now uses an internal effective prompt when the user message is empty but file sources are available. ### Deprecated - None. ### Removed - None. ### Fixed - Fixed empty-prompt file uploads not injecting collected file context into the model message. - Fixed query-based RAG running with an empty prompt for file-only turns. - Fixed native tool citation context rebuilding to use the preserved original/effective user prompt instead of a potentially already-templated RAG message. ### Security - None. ### Breaking Changes - None. --- ### Additional Information - Query-based RAG requires a meaningful user query. When the user attaches a file without typing a prompt, there is no reliable query to use for semantic retrieval. In that case, using the existing full-context path is more deterministic and matches the user's implicit intent: use the attached document in the current conversation. - This preserves the existing query-based RAG behavior when the user does provide a prompt. - This reuses the existing full-context file handling path rather than adding a new setting. ### Testing - Manual reproduction before the fix: - Attach/upload a document. - Send the message with no typed prompt. - The model responds as if no task/context was provided, such as saying it is ready for instructions. - Expected behavior after the fix: - Attach/upload a document. - Send the message with no typed prompt. - The backend treats the turn as full-context file usage and injects the file context with an internal effective prompt, allowing the model to respond based on the attached document and conversation context. ### Screenshots or Videos - Not included. This is a backend chat payload/context handling fix. ### Contributor License Agreement  - [x] 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 2026-04-30 03:19:58 -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#50554