This is a powerful PDF Document-based Question Answering System using using Retrieval Augmented Generation. By the power of LlamaIndex, Llama2 model using Gradient's LLM, seamlessly merged with superfast Apache Cassandra as a vector database.
Deploy the file after setting up the virtual environment with:
streamlit run chatwithpdf.py
The system can be deployed and utilized through FastAPI in the main.py file. First Install uvicorn:
pip install "uvicorn[standard]"
Run the Server Program
uvicorn.run(app, host="127.0.0.1", port=5000)