Bayani is a multilingual (English and Hausa) document question-answering application built with Streamlit and LangChain. It allows users to upload documents and ask questions about their content in multiple languages.
- Document upload and processing (PDF support)
- Multilingual interface (English and Hausa)
- Interactive chat interface
- Source reference for answers
- Python 3.11+
- OpenAI API key
- Clone the repository:
git clone [https://github.com/ufakz/bayani](https://github.com/ufakz/bayani)
cd bayani
- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Set up your OpenAI API key:
export OPENAI_API_KEY='your-api-key-here'
- Start the application:
streamlit run main.py
- Select your preferred language from the sidebar
- Upload your PDF documents
- Click "Process Documents" to analyze them
- Start asking questions about your documents in the chat interface
- streamlit
- langchain
- langchain-openai
- langchain-core
- PyPDF2
- python-dotenv