| title: Universal Document Intelligence Chatbot | |
| emoji: π | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: streamlit | |
| sdk_version: 1.28.0 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # π Universal Document Intelligence Chatbot | |
| [](https://streamlit.io) | |
| [](https://huggingface.co) | |
| [](https://python.org) | |
| A simple, private, and powerful chatbot that can answer your questions using both your own documents and the web. | |
| ## β¨ Features | |
| - **π Runs locally**: Uses Hugging Face Transformers, so your data stays private | |
| - **β‘ Quick search**: Finds answers fast with Sentence Transformers and FAISS | |
| - **π§ Smart routing**: Decides when to pull from your documents or from the web | |
| - **π Handles PDFs**: Upload PDFs and ask questions directly | |
| - **π Stay up to date**: Can use web search for the latest information | |
| - **π¦ No setup hassle**: Downloads models automatically the first time you use them | |
| ## π Quick Start | |
| ### Local Setup | |
| ```bash | |
| # Create a virtual environment | |
| python -m venv venv | |
| # Activate it (Windows) | |
| venv\Scripts\activate.bat | |
| # Activate it (Mac/Linux) | |
| source venv/bin/activate | |
| # Install dependencies | |
| pip install -r requirements.txt | |
| # Launch the app | |
| streamlit run app.py | |