| --- |
| title: sui-1 Summarizer |
| emoji: 📄 |
| colorFrom: indigo |
| colorTo: purple |
| sdk: gradio |
| sdk_version: 5.34.2 |
| app_file: app.py |
| pinned: false |
| license: mit |
| short_description: Grounded Summarization with Source Citations |
| --- |
| |
| # sui-1 Summarizer |
|
|
| Generate grounded summaries with verifiable source citations using the [ellamind/sui-1-24b](https://huggingface.co/ellamind/sui-1-24b) model. |
|
|
| ## Features |
|
|
| - **PDF Upload**: Extract text using Mistral OCR |
| - **Text Input**: Paste text directly for summarization |
| - **Multi-language**: Support for English, German, Spanish, French, and Italian |
| - **Source Citations**: Every claim is backed by numbered citations from the source document |
| - **Streaming Output**: See the summary generate in real-time |
|
|
| ## Requirements |
|
|
| This Space requires: |
| - **ZeroGPU** hardware (uses `@spaces.GPU` decorator) |
| - **MISTRAL_API_KEY** secret for PDF OCR functionality |
|
|
| ## Setup |
|
|
| 1. Create a new Space on HuggingFace |
| 2. Set the hardware to **ZeroGPU** |
| 3. Add `MISTRAL_API_KEY` as a secret in Space settings |
| 4. Upload `app.py`, `requirements.txt`, and this `README.md` |
|
|
