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 to validate 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 clearly categorize this pull request, prefix the pull request title using one of the following:
feat: Introduces a new feature or enhancement to the codebase
Changelog Entry
Description
As proposed in discussion #11386 and #12062, this PR introduces Mistral OCR support for PDF content extraction within Open Web UI. Mistral OCR excels at interpreting complex document elements—including images, math, tables, and LaTeX layouts—enabling deeper understanding of rich documents like scientific papers with charts, graphs, and equations.
I added support for Mistral OCR integration into the backend and frontend of Open Web UI. The changes include adding configuration options, implementing the Mistral OCR loader, and updating the relevant components to handle the new OCR engine.
Added
Added MISTRAL_OCR_API_KEY configuration in backend/open_webui/config.py and updated the application state to include this key (backend/open_webui/config.py, backend/open_webui/main.py, backend/open_webui/routers/retrieval.py).
Implemented MistralLoader class for handling OCR processing via Mistral API in backend/open_webui/retrieval/loaders/mistral.py.
Added Mistral OCR configuration fields and validation in src/lib/components/admin/Settings/Documents.svelte.
Changed
Changed the _get_loader method in backend/open_webui/retrieval/loaders/main.py to include the Mistral OCR loader.
Deprecated
None
Removed
None
Fixed
None
Security
None
Breaking Changes
None
Additional Information
Implemented just with requests. No additional python package needed.
The document is divided into pages.
Screenshots or Videos
🔄 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/12307
**Author:** [@paddy313](https://github.com/paddy313)
**Created:** 4/1/2025
**Status:** ✅ Merged
**Merged:** 4/2/2025
**Merged by:** [@tjbck](https://github.com/tjbck)
**Base:** `dev` ← **Head:** `feature/mistral_ocr`
---
### 📝 Commits (4)
- [`1ac6879`](https://github.com/open-webui/open-webui/commit/1ac6879268e3526bf71006b46b6cc45d281eda87) Add Mistral OCR integration and configuration support
- [`93d7702`](https://github.com/open-webui/open-webui/commit/93d7702e8c889361e4198a12038fdcccd5f83505) refactor: move MistralLoader to a separate module and just use the requests package instead of mistralai
- [`c5a8d2f`](https://github.com/open-webui/open-webui/commit/c5a8d2f8571a801dffd4795eec2eb616cf9260d3) refactor: update MistralLoader documentation and adjust parameters for signed URL retrieval
- [`0ac00b9`](https://github.com/open-webui/open-webui/commit/0ac00b92569bd023de08c73663e6fe2314564e11) refactor: update import path for MistralLoader
### 📊 Changes
**6 files changed** (+282 additions, -5 deletions)
<details>
<summary>View changed files</summary>
📝 `backend/open_webui/config.py` (+5 -0)
📝 `backend/open_webui/main.py` (+2 -0)
📝 `backend/open_webui/retrieval/loaders/main.py` (+12 -0)
➕ `backend/open_webui/retrieval/loaders/mistral.py` (+225 -0)
📝 `backend/open_webui/routers/retrieval.py` (+16 -0)
📝 `src/lib/components/admin/Settings/Documents.svelte` (+22 -5)
</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.
- [ ] **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?
- [ ] **Testing:** Have you written and run sufficient tests to validate 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 clearly categorize this pull request, prefix the pull request title using one of the following:
- **feat**: Introduces a new feature or enhancement to the codebase
# Changelog Entry
### Description
As proposed in discussion #11386 and #12062, this PR introduces Mistral OCR support for PDF content extraction within Open Web UI. [Mistral OCR](https://mistral.ai/news/mistral-ocr) excels at interpreting complex document elements—including images, math, tables, and LaTeX layouts—enabling deeper understanding of rich documents like scientific papers with charts, graphs, and equations.
I added support for Mistral OCR integration into the backend and frontend of Open Web UI. The changes include adding configuration options, implementing the Mistral OCR loader, and updating the relevant components to handle the new OCR engine.
### Added
- Added `MISTRAL_OCR_API_KEY` configuration in `backend/open_webui/config.py` and updated the application state to include this key (`backend/open_webui/config.py`, `backend/open_webui/main.py`, `backend/open_webui/routers/retrieval.py`).
- Implemented `MistralLoader` class for handling OCR processing via Mistral API in `backend/open_webui/retrieval/loaders/mistral.py`.
- Added Mistral OCR configuration fields and validation in `src/lib/components/admin/Settings/Documents.svelte`.
### Changed
- Changed the `_get_loader` method in `backend/open_webui/retrieval/loaders/main.py` to include the Mistral OCR loader.
### Deprecated
- None
### Removed
- None
### Fixed
- None
### Security
- None
### Breaking Changes
- None
---
### Additional Information
- Implemented just with requests. No additional python package needed.
- The document is divided into pages.
### Screenshots or Videos
---
<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/12307
Author: @paddy313
Created: 4/1/2025
Status: ✅ Merged
Merged: 4/2/2025
Merged by: @tjbck
Base:
dev← Head:feature/mistral_ocr📝 Commits (4)
1ac6879Add Mistral OCR integration and configuration support93d7702refactor: move MistralLoader to a separate module and just use the requests package instead of mistralaic5a8d2frefactor: update MistralLoader documentation and adjust parameters for signed URL retrieval0ac00b9refactor: update import path for MistralLoader📊 Changes
6 files changed (+282 additions, -5 deletions)
View changed files
📝
backend/open_webui/config.py(+5 -0)📝
backend/open_webui/main.py(+2 -0)📝
backend/open_webui/retrieval/loaders/main.py(+12 -0)➕
backend/open_webui/retrieval/loaders/mistral.py(+225 -0)📝
backend/open_webui/routers/retrieval.py(+16 -0)📝
src/lib/components/admin/Settings/Documents.svelte(+22 -5)📄 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
As proposed in discussion #11386 and #12062, this PR introduces Mistral OCR support for PDF content extraction within Open Web UI. Mistral OCR excels at interpreting complex document elements—including images, math, tables, and LaTeX layouts—enabling deeper understanding of rich documents like scientific papers with charts, graphs, and equations.
I added support for Mistral OCR integration into the backend and frontend of Open Web UI. The changes include adding configuration options, implementing the Mistral OCR loader, and updating the relevant components to handle the new OCR engine.
Added
MISTRAL_OCR_API_KEYconfiguration inbackend/open_webui/config.pyand updated the application state to include this key (backend/open_webui/config.py,backend/open_webui/main.py,backend/open_webui/routers/retrieval.py).MistralLoaderclass for handling OCR processing via Mistral API inbackend/open_webui/retrieval/loaders/mistral.py.src/lib/components/admin/Settings/Documents.svelte.Changed
_get_loadermethod inbackend/open_webui/retrieval/loaders/main.pyto include the Mistral OCR loader.Deprecated
Removed
Fixed
Security
Breaking Changes
Additional Information
Screenshots or Videos
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.