RADD is an intelligent document analysis tool that leverages advanced NLP models to extract, classify, and visualize insights from text files. Built with Streamlit, Transformers, Torch, and Pandas.
- 📤 Upload and process various text-based documents
- 🤖 Apply pre-trained or custom NLP models (e.g., BERT, RoBERTa)
- 📊 Visualize predictions and document insights
- ⚡ Real-time interactive UI using Streamlit
- 🧹 Efficient text handling with Pandas
| Technology | Purpose |
|---|---|
| Streamlit | Interactive web UI |
| Transformers | NLP model inference |
| PyTorch | Deep learning model backend |
| Pandas | Data preprocessing and analysis |
git clone https://github.com/Pranaykamble000/radd.git
cd radd
## 🛠 Create a virtual environment
python -m venv env
env\Scripts\activate
## 📦 Install Independencies
pip install -r requirements.txt
## Run the Streamlit app
streamlit run app.py
## 📂 Project Structure
radd/
├── app.py # Streamlit main app
├── model/ # Pre-trained models or checkpoints
├── utils/ # Helper scripts (e.g., preprocessing)
├── data/ # Sample input/output files
├── requirements.txt # Dependencies list
└── README.md # Project documentation
### 📄 License
This project is licensed under the **MIT License**.
See the [LICENSE](./LICENSE) file for more details.
### 🙌 Acknowledgments
Streamlit – For building elegant, interactive web apps effortlessly.
HuggingFace Transformers – For access to state-of-the-art NLP models.
PyTorch – For providing the deep learning engine.
Pandas – For powerful data manipulation tools.
###✨ Author
Pranay Kamble
📫 GitHub: @Pranaykamble000
Let me know if you want to:
- Add deployment steps (e.g., on Streamlit Cloud or Heroku)
- Include a demo video/GIF
- Automatically download models when the app runs
Happy building!