Spaces:
Sleeping
Sleeping
title: ResearchpaperSummarizer | |
emoji: π» | |
colorFrom: green | |
colorTo: purple | |
sdk: gradio | |
sdk_version: 5.29.1 | |
app_file: app.py | |
pinned: false | |
# π§ Research Paper Summarizer | |
 | |
 | |
[](https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer) | |
Welcome to the **Research Paper Summarizer** β a powerful tool designed to automatically extract and summarize text from research paper images or PDFs, while identifying key subdomains and technical topics covered in the document. | |
--- | |
## π Live Demo | |
β‘οΈ **Try it now on Hugging Face Spaces**: | |
π [https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer](https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer) | |
--- | |
## π Features | |
- π· Upload **research paper screenshots** or **PDFs** | |
- π Automatic **OCR-based text extraction** using `EasyOCR` | |
- π§ Summarization and **key subdomain detection** using `LLaMA 3` via `Langchain + Groq API` | |
- β Simple and clean **Gradio interface** | |
--- | |
## π How It Works | |
1. **Upload** a research paper image or PDF. | |
2. The system performs **OCR** to extract readable text. | |
3. A custom prompt is sent to **LLaMA 3.3** using the `Groq API`. | |
4. The app returns: | |
- A concise **summary** | |
- A list of **key subdomains & topics** covered | |
--- | |
## π Tech Stack | |
- π§ **[LLaMA 3.3 -70B](https://huggingface.co/meta-llama)** via Groq API | |
- π§Ύ **EasyOCR** for image-to-text | |
- βοΈ **Langchain** for structured prompt engineering | |
- πΌ **OpenCV** and **pdf2image** for input handling | |
- π **Gradio** for UI | |
- βοΈ **Deployed on Hugging Face Spaces** | |
--- | |
## π¦ Requirements | |
To run this app locally, install the following: | |
```bash | |
pip install -r requirements.txt | |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |