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 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
Traditional web scraping methods like the safe_web mode can sometimes provide lower quality results due to dynamic page elements loading in through JavaScript. By utilizing playwright, we can allow these items to load and be retrieved.
Introduction of playwright support could indirectly benefit Tools and Functions by enabling web browsing agents in the future
I've enabled support for two modes: Playwright Server in a separate container, or optionally installing chromium dependencies directly in the Open WebUI container on launch
Added
Added environment variables:
RAG_WEB_LOADER (can be safe_web or playwright)
PLAYWRIGHT_WS_URI (can be None or ws:// something)
Added dependency: playwright==1.49.1
Introduce ability to switch out WebLoaderClass with the existing SafeWebBaseLoader OR the new SafePlaywrightURLLoader
Supported RAG_WEB_SEARCH_TRUST_ENV in new implementation (SafePlaywrightURLLoader)
In startup scripts, automatically download chromium for playwright when no PLAYWRIGHT_WS_URI is specified
In startup scripts, automatically download nltk tokenizer "punkt_tab" for unstructured inside SafePlaywrightURLLoader when in playwright mode
Changed
Updated unstructured from 0.16.11 to 0.16.17 (this fixes issues with downloading nltk tokenizer)
Please let me know if I need to do or change anything!
🔄 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/10052
**Author:** [@roryeckel](https://github.com/roryeckel)
**Created:** 2/15/2025
**Status:** ✅ Merged
**Merged:** 2/19/2025
**Merged by:** [@tjbck](https://github.com/tjbck)
**Base:** `dev` ← **Head:** `playwright`
---
### 📝 Commits (10+)
- [`4e8b390`](https://github.com/open-webui/open-webui/commit/4e8b3906821a9a10f4fd0038373291dff41b65cf) Add RAG_WEB_LOADER + Playwright mode + improve stability of search
- [`8dafe3c`](https://github.com/open-webui/open-webui/commit/8dafe3cba8c9166e33298f1c640b2bec974c5612) Merge branch 'dev' of https://github.com/open-webui/open-webui
- [`2452e27`](https://github.com/open-webui/open-webui/commit/2452e271cddccf0c835ae17f4505471eb41a4313) Refine RAG_WEB_LOADER
- [`77ae73e`](https://github.com/open-webui/open-webui/commit/77ae73e659e6fea6da34c3ea913edb3dc4f037a9) Adjust search event messages + translations
- [`a84e488`](https://github.com/open-webui/open-webui/commit/a84e488a4ea681c580a2b9cca22fe176f8c0014c) Fix playwright in docker by updating unstructured
- [`8da3372`](https://github.com/open-webui/open-webui/commit/8da33721d563754becd0d03bf86605441e0bd9e3) Support PLAYWRIGHT_WS_URI
- [`c3df481`](https://github.com/open-webui/open-webui/commit/c3df481b22d8bc13a7deb045e94b0bcf4235224e) Introduce docker-compose.playwright.yaml + run-compose update
- [`f837d2c`](https://github.com/open-webui/open-webui/commit/f837d2cdbb40642b157d936c936cdf8eadc44ef3) Merge branch 'dev' of https://github.com/open-webui/open-webui
- [`22746c7`](https://github.com/open-webui/open-webui/commit/22746c7a3f86f6f49c8eb3ded3bc45d407f68177) Merge remote-tracking branch 'upstream/dev'
- [`1b581b7`](https://github.com/open-webui/open-webui/commit/1b581b714f6749e51bf17c49434976a0c57900c6) Moving code out of playwright branch
### 📊 Changes
**11 files changed** (+279 additions, -34 deletions)
<details>
<summary>View changed files</summary>
📝 `backend/open_webui/config.py` (+12 -0)
📝 `backend/open_webui/main.py` (+4 -0)
📝 `backend/open_webui/retrieval/web/utils.py` (+216 -29)
📝 `backend/open_webui/routers/retrieval.py` (+1 -1)
📝 `backend/open_webui/utils/middleware.py` (+1 -1)
📝 `backend/requirements.txt` (+2 -2)
📝 `backend/start.sh` (+11 -0)
📝 `backend/start_windows.bat` (+11 -0)
➕ `docker-compose.playwright.yaml` (+10 -0)
📝 `pyproject.toml` (+2 -1)
📝 `run-compose.sh` (+9 -0)
</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?
- [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
- [x] **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 PR is a revision of https://github.com/open-webui/open-webui/pull/9313 intended to resolve https://github.com/open-webui/open-webui/issues/2617
- Traditional web scraping methods like the safe_web mode can sometimes provide lower quality results due to dynamic page elements loading in through JavaScript. By utilizing playwright, we can allow these items to load and be retrieved.
- Introduction of playwright support could indirectly benefit Tools and Functions by enabling web browsing agents in the future
- I've enabled support for two modes: Playwright Server in a separate container, or optionally installing chromium dependencies directly in the Open WebUI container on launch
### Added
- Added environment variables:
- RAG_WEB_LOADER (can be safe_web or playwright)
- PLAYWRIGHT_WS_URI (can be None or ws:// something)
- Added dependency: playwright==1.49.1
- Introduce ability to switch out WebLoaderClass with the existing SafeWebBaseLoader OR the new SafePlaywrightURLLoader
- Supported RAG_WEB_SEARCH_TRUST_ENV in new implementation (SafePlaywrightURLLoader)
- In startup scripts, automatically download chromium for playwright when no PLAYWRIGHT_WS_URI is specified
- In startup scripts, automatically download nltk tokenizer "punkt_tab" for unstructured inside SafePlaywrightURLLoader when in playwright mode
### Changed
- Updated unstructured from 0.16.11 to 0.16.17 (this fixes issues with downloading nltk tokenizer)
### Deprecated
- None
### Removed
- None
### Fixed
- None
### Security
- None
### Breaking Changes
- None
---
### Additional Information
- I've updated the relevant documentation for my feature here: https://github.com/open-webui/docs/compare/main...roryeckel:open-webui-docs:main but haven't opened a PR for the docs yet.
- Please let me know if I need to do or change anything!
---
<sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
📋 Pull Request Information
Original PR: https://github.com/open-webui/open-webui/pull/10052
Author: @roryeckel
Created: 2/15/2025
Status: ✅ Merged
Merged: 2/19/2025
Merged by: @tjbck
Base:
dev← Head:playwright📝 Commits (10+)
4e8b390Add RAG_WEB_LOADER + Playwright mode + improve stability of search8dafe3cMerge branch 'dev' of https://github.com/open-webui/open-webui2452e27Refine RAG_WEB_LOADER77ae73eAdjust search event messages + translationsa84e488Fix playwright in docker by updating unstructured8da3372Support PLAYWRIGHT_WS_URIc3df481Introduce docker-compose.playwright.yaml + run-compose updatef837d2cMerge branch 'dev' of https://github.com/open-webui/open-webui22746c7Merge remote-tracking branch 'upstream/dev'1b581b7Moving code out of playwright branch📊 Changes
11 files changed (+279 additions, -34 deletions)
View changed files
📝
backend/open_webui/config.py(+12 -0)📝
backend/open_webui/main.py(+4 -0)📝
backend/open_webui/retrieval/web/utils.py(+216 -29)📝
backend/open_webui/routers/retrieval.py(+1 -1)📝
backend/open_webui/utils/middleware.py(+1 -1)📝
backend/requirements.txt(+2 -2)📝
backend/start.sh(+11 -0)📝
backend/start_windows.bat(+11 -0)➕
docker-compose.playwright.yaml(+10 -0)📝
pyproject.toml(+2 -1)📝
run-compose.sh(+9 -0)📄 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:
devbranch.Changelog Entry
Description
This PR is a revision of https://github.com/open-webui/open-webui/pull/9313 intended to resolve https://github.com/open-webui/open-webui/issues/2617
Added
Changed
Deprecated
Removed
Fixed
Security
Breaking Changes
Additional Information
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.