🔄 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/1050
**Author:** [@jannikstdl](https://github.com/jannikstdl)
**Created:** 3/5/2024
**Status:** ✅ Merged
**Merged:** 3/6/2024
**Merged by:** [@tjbck](https://github.com/tjbck)
**Base:** `dev` ← **Head:** `rag-pdf-ocr`
---
### 📝 Commits (1)
- [`089a63e`](https://github.com/open-webui/open-webui/commit/089a63e0c68bb1c2693a15a8469a278dc358b111) feat: added ocr functionality to the pdf loader
### 📊 Changes
**2 files changed** (+2 additions, -1 deletions)
<details>
<summary>View changed files</summary>
📝 `backend/apps/rag/main.py` (+1 -1)
📝 `backend/requirements.txt` (+1 -0)
</details>
### 📄 Description
Added OCR functionality to the PDF loader.
File used for the test:
[This is a pdf file with a screenshot.pdf](https://github.com/open-webui/open-webui/files/14501663/This.is.a.pdf.file.with.a.screenshot.pdf)
Before:

After:

Ressources:
[langchain](https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf#extracting-images)
---
<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/1050
Author: @jannikstdl
Created: 3/5/2024
Status: ✅ Merged
Merged: 3/6/2024
Merged by: @tjbck
Base:
dev← Head:rag-pdf-ocr📝 Commits (1)
089a63efeat: added ocr functionality to the pdf loader📊 Changes
2 files changed (+2 additions, -1 deletions)
View changed files
📝
backend/apps/rag/main.py(+1 -1)📝
backend/requirements.txt(+1 -0)📄 Description
Added OCR functionality to the PDF loader.
File used for the test:
This is a pdf file with a screenshot.pdf
Before:

After:

Ressources:
langchain
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.