[PR #3078] [CLOSED] Implement domain whitelisting for web search results #36810

New Issue

2026-04-25T10:32:53-05:00

GiteaMirror commented

2026-04-25 10:32:53 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/3078
Author: @que-nguyen
Created: 6/12/2024
Status: ❌ Closed

Base: dev ← Head: whitelist-websearch

📝 Commits (10+)

c41b33c Merge pull request #3013 from open-webui/dev
0917fa6 Merge pull request #3056 from open-webui/dev
47ac0fb Define configuration variable RAG_WEB_SEARCH_WHITE_LIST_DOMAINS
5bdf7c9 Implemented filter_by_whitelist function
ffb06e7 Implement domain whitelisting for BRAVE search results
242be8b Implement domain whitelisting for DUCKDUCKGO search results
314f2fb Implement domain whitelisting for GOOGLE_PSE search results
8feced3 Implement domain whitelisting for SEARXNG search results
38cf4c7 Implement domain whitelisting for SERPER search results
e031a7e Implement domain whitelisting for SERPLY search results

📊 Changes

10 files changed (+68 additions, -32 deletions)

View changed files

📝 backend/apps/rag/main.py (+9 -1)
📝 backend/apps/rag/search/brave.py (+5 -4)
📝 backend/apps/rag/search/duckduckgo.py (+6 -5)
📝 backend/apps/rag/search/google_pse.py (+5 -4)
📝 backend/apps/rag/search/main.py (+11 -1)
📝 backend/apps/rag/search/searxng.py (+8 -5)
📝 backend/apps/rag/search/serper.py (+5 -4)
📝 backend/apps/rag/search/serply.py (+5 -4)
📝 backend/apps/rag/search/serpstack.py (+5 -4)
📝 backend/config.py (+9 -0)

📄 Description

Note: Meta search engines like SearxNG do not support filtering results by domain natively, so this filtering is applied post-search.
Added a filter to restrict search results to specified domains.
Updated the processing of search results to apply the whitelist filter before returning the final results.
Ensured that only results from allowed domains (if specified in the whitelist) are included in the output.

_{🔄 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/3078 **Author:** [@que-nguyen](https://github.com/que-nguyen) **Created:** 6/12/2024 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `whitelist-websearch` --- ### 📝 Commits (10+) - [`c41b33c`](https://github.com/open-webui/open-webui/commit/c41b33c9c0722c84055a833802611f8ee39609d3) Merge pull request #3013 from open-webui/dev - [`0917fa6`](https://github.com/open-webui/open-webui/commit/0917fa6f4ac015810211d85eb41da5d335762952) Merge pull request #3056 from open-webui/dev - [`47ac0fb`](https://github.com/open-webui/open-webui/commit/47ac0fba098c9c7686d7d820627bcdbfebfdff2a) Define configuration variable RAG_WEB_SEARCH_WHITE_LIST_DOMAINS - [`5bdf7c9`](https://github.com/open-webui/open-webui/commit/5bdf7c9dcc91662a418140cfefd71d5ae3835aee) Implemented filter_by_whitelist function - [`ffb06e7`](https://github.com/open-webui/open-webui/commit/ffb06e7193366bd8a129e336125910cfacdf8576) Implement domain whitelisting for BRAVE search results - [`242be8b`](https://github.com/open-webui/open-webui/commit/242be8b2e9b358fb6a3245da7dc5ada649209704) Implement domain whitelisting for DUCKDUCKGO search results - [`314f2fb`](https://github.com/open-webui/open-webui/commit/314f2fb157fbc40c139aada8c4c159fc34757805) Implement domain whitelisting for GOOGLE_PSE search results - [`8feced3`](https://github.com/open-webui/open-webui/commit/8feced357c778343d45f8804e06a0de124cdcea0) Implement domain whitelisting for SEARXNG search results - [`38cf4c7`](https://github.com/open-webui/open-webui/commit/38cf4c7898e9d08b75de9086ff6eeb41e6fe83df) Implement domain whitelisting for SERPER search results - [`e031a7e`](https://github.com/open-webui/open-webui/commit/e031a7eb6ceab37b7e2ad238a6e853b3ecfaed7a) Implement domain whitelisting for SERPLY search results ### 📊 Changes **10 files changed** (+68 additions, -32 deletions) <details> <summary>View changed files</summary> 📝 `backend/apps/rag/main.py` (+9 -1) 📝 `backend/apps/rag/search/brave.py` (+5 -4) 📝 `backend/apps/rag/search/duckduckgo.py` (+6 -5) 📝 `backend/apps/rag/search/google_pse.py` (+5 -4) 📝 `backend/apps/rag/search/main.py` (+11 -1) 📝 `backend/apps/rag/search/searxng.py` (+8 -5) 📝 `backend/apps/rag/search/serper.py` (+5 -4) 📝 `backend/apps/rag/search/serply.py` (+5 -4) 📝 `backend/apps/rag/search/serpstack.py` (+5 -4) 📝 `backend/config.py` (+9 -0) </details> ### 📄 Description - Note: Meta search engines like SearxNG do not support filtering results by domain natively, so this filtering is applied post-search. - Added a filter to restrict search results to specified domains. - Updated the processing of search results to apply the whitelist filter before returning the final results. - Ensured that only results from allowed domains (if specified in the whitelist) are included in the output. --- <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 2026-04-25 10:32:53 -05:00

GiteaMirror closed this issue

2026-04-25 10:32:54 -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#36810