The PDF-ingestion-QnA-App based on RAG(Retrieval-augmented generation) is a powerful application that allows users to upload PDF documents and ask questions based on the content of those documents. Leveraging advanced language models and retrieval-augmented generation techniques, this application provides concise and accurate answers from the uploaded PDFs.
- Upload and process PDF documents.
- Ask questions about the content of the uploaded PDFs.
- Efficient text splitting and embedding using state-of-the-art models.
- In-memory vector storage for fast retrieval of document chunks.
- User-friendly interface built with Streamlit.
- Python: The programming language used for the implementation.
- LangChain: A framework for developing applications with language models.
- Streamlit: A library for building interactive web applications.
- Hugging Face: For pre-trained models and embeddings.
- Groq: For efficient model execution.
To get started with the PDF Q&A System, follow these steps:
- Clone the repository:
git clone https://github.com/vishnun0027/PDF-ingestion-QnA-App.git PDF-ingestion-QnA-App
2.Install the required packages:
pip install -r requirements.txt- Set up environment variables: Create a .env file in the root directory of the project and add your API keys:
GROQ_API_KEY=your_groq_api_key
HF_API_KEY=your_hugging_face_api_key-
Run the Streamlit application:
-
run app
streamlit run app.py
-
Upload a PDF: Use the sidebar to upload your PDF document.
-
Ask Questions: After processing, enter your questions in the chat input field to receive answers based on the content of the PDF.