[PR #11324] [MERGED] fix: opensearch vector db query structures, result mapping, filters, bulk query actions, knn_vector usage #45758

New Issue

GiteaMirror · 2026-04-29T20:16:33-05:00

GiteaMirror commented

2026-04-29 20:16:33 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/11324
Author: @kela4
Created: 3/6/2025
Status: ✅ Merged
Merged: 3/8/2025
Merged by: @tjbck

Base: dev ← Head: main

📝 Commits (2)

3b70cd6 Merge pull request #11257 from open-webui/dev
6cb0c03 fix: opensearch vector db query structures, result mapping, filters, bulk query actions, knn_vector usage

📊 Changes

1 file changed (+120 additions, -64 deletions)

View changed files

📝 backend/open_webui/retrieval/vector/dbs/opensearch.py (+120 -64)

📄 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. #11174

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

This pull request fixes various errors that previously occurred when trying to use OpenSearch as a vector db. Errors have occurred when trying to upload documents to a chat with OpenSearch as a vector db, or when trying to create a knowledge base of documents and asking quesions regarding the documents. These errors are caused, for example, by the fact that the queries and the query syntax have not yet been fully adapted to OpenSearch and, for example, a different type of index needs to be used because the previously specified type is not supported by OpenSearch.
With the changes it will be possible to use OpenSearch as vector db without the previous errors while uploading and using documents in a chat or in a knowledge base, because the PR fixes the queries etc. It was tested using OpenSearch version 2.19.1.

Added

add handling of empty search results in the mapping of the OpenSearch result to GetResult and SearchResult
add handling of failed search query
add _get_index_name method to simplify the usage of the compounded index name

Fixed

fix list-structure in the mapping of the OpenSearch result to GetResult and SearchResult
fix creation of index - uses OpenSearch knn_vector now instead of the not supported dense_vector
fix search query structure
fix handling of filters in query - now they are applied to the right fields
fix bulk query actions in insert, upsert and delete method - with the previous used bulk method, it would have been necessary to pass the index as a separate addition json object (what was not done), the now used bulk-handler supports the direct specification of the index in only one json object per action
fix delete function by adding filter parameter to delete function - this allows to remove the documents correctly, e.g. by file_id
fix _create_index_if_not_exists replace has_index with has_collection - OpenSearchClient has no has_index method

_{🔄 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/11324 **Author:** [@kela4](https://github.com/kela4) **Created:** 3/6/2025 **Status:** ✅ Merged **Merged:** 3/8/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `main` --- ### 📝 Commits (2) - [`3b70cd6`](https://github.com/open-webui/open-webui/commit/3b70cd64d7fa6902e8c79cf8dcbf3c7e84cf704b) Merge pull request #11257 from open-webui/dev - [`6cb0c03`](https://github.com/open-webui/open-webui/commit/6cb0c0339a28b3e9d5399cff37fd68c9888f9a5f) fix: opensearch vector db query structures, result mapping, filters, bulk query actions, knn_vector usage ### 📊 Changes **1 file changed** (+120 additions, -64 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/retrieval/vector/dbs/opensearch.py` (+120 -64) </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. #11174 **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. - [ ] **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 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 - This pull request fixes various errors that previously occurred when trying to use OpenSearch as a vector db. Errors have occurred when trying to upload documents to a chat with OpenSearch as a vector db, or when trying to create a knowledge base of documents and asking quesions regarding the documents. These errors are caused, for example, by the fact that the queries and the query syntax have not yet been fully adapted to OpenSearch and, for example, a different type of index needs to be used because the previously specified type is not supported by OpenSearch. - With the changes it will be possible to use OpenSearch as vector db without the previous errors while uploading and using documents in a chat or in a knowledge base, because the PR fixes the queries etc. It was tested using OpenSearch version 2.19.1. ### Added - add handling of empty search results in the mapping of the OpenSearch result to GetResult and SearchResult - add handling of failed search query - add _get_index_name method to simplify the usage of the compounded index name ### Fixed - fix list-structure in the mapping of the OpenSearch result to GetResult and SearchResult - fix creation of index - uses OpenSearch knn_vector now instead of the not supported dense_vector - fix search query structure - fix handling of filters in query - now they are applied to the right fields - fix bulk query actions in insert, upsert and delete method - with the previous used bulk method, it would have been necessary to pass the index as a separate addition json object (what was not done), the now used bulk-handler supports the direct specification of the index in only one json object per action - fix delete function by adding filter parameter to delete function - this allows to remove the documents correctly, e.g. by file_id - fix _create_index_if_not_exists replace has_index with has_collection - OpenSearchClient has no has_index method --- --- <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 2026-04-29 20:16:33 -05:00

GiteaMirror closed this issue

2026-04-29 20:16:34 -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#45758