---
title: InsightOCR
emoji: 💻
colorFrom: pink
colorTo: blue
sdk: gradio
sdk_version: 5.40.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: OCR + GPT-4 powered insight extractor for printed and handwr
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
# OCR and Insight Generator

This is a Gradio app that allows users to upload an image containing printed or handwritten text. It uses:

- **Qwen2.5-VL-7B-Instruct** (via Hugging Face) to extract text from the image
- **GPT-4.1-mini** (via OpenAI) to analyze the extracted text and return structured insights in Arabic

## Usage

1. Add your `.env` file with:
   ```
   HF_TOKEN=your_huggingface_token
   OPENAI_API_KEY=your_openai_key
   ```

2. Run locally with:
   ```
   python app.py
   ```

3. Or deploy to Hugging Face Spaces.

## Deploying to Hugging Face Spaces

- Create a new Space (SDK: Gradio)
- Push this repo (with `app.py`, `requirements.txt`, and `README.md`)