[PR #1029] [MERGED] recreate rag collection instead of falling back to stale version #91597

New Issue

GiteaMirror · 2026-05-15T16:59:47-05:00

GiteaMirror commented

2026-05-15 16:59:47 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/1029
Author: @fbirlik
Created: 3/4/2024
Status: ✅ Merged
Merged: 3/4/2024
Merged by: @tjbck

Base: dev ← Head: patch-ragrecreate

📝 Commits (2)

5d4ff85 recreate rag collection instead of falling back to stale version
6782e95 recreate rag collection is now optional and only used for web requests

📊 Changes

1 file changed (+8 additions, -2 deletions)

View changed files

📝 backend/apps/rag/main.py (+8 -2)

📄 Description

Description

store_data_in_vector_db is used to store web pages after retrieval. Currently, new version of the page is retrieved, split into chunks, but because previous collection exists, new data is dropped. Queries are executed against previous version instead of latest.

Changelog Entry

Changed

check for existence of previous version of the collection and delete it if exists; this ensure new version is stored and used in further queries

_{🔄 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/1029 **Author:** [@fbirlik](https://github.com/fbirlik) **Created:** 3/4/2024 **Status:** ✅ Merged **Merged:** 3/4/2024 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `patch-ragrecreate` --- ### 📝 Commits (2) - [`5d4ff85`](https://github.com/open-webui/open-webui/commit/5d4ff852281cf18dac9955442b60737e25447257) recreate rag collection instead of falling back to stale version - [`6782e95`](https://github.com/open-webui/open-webui/commit/6782e95c7584defd990bb01cf2732f721038d190) recreate rag collection is now optional and only used for web requests ### 📊 Changes **1 file changed** (+8 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `backend/apps/rag/main.py` (+8 -2) </details> ### 📄 Description ## Description store_data_in_vector_db is used to store web pages after retrieval. Currently, new version of the page is retrieved, split into chunks, but because previous collection exists, new data is dropped. Queries are executed against previous version instead of latest. --- ### Changelog Entry ### Changed - check for existence of previous version of the collection and delete it if exists; this ensure new version is stored and used in further queries --- <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 2026-05-15 16:59:47 -05:00

GiteaMirror closed this issue

2026-05-15 16:59:50 -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#91597