This application enables users to upload PDF files, process their content, and interact with them through a user-friendly interface. By leveraging advanced NLP models and a vector database, users can ask questions and receive accurate, context-aware answers from the uploaded documents.
- Upload the PDF
- Ask the Quetions
- PDF Upload: Upload multiple PDFs for content analysis.
- Text Processing: Automatically extracts and splits PDF text into manageable chunks.
- Vector Storage: Stores and retrieves document embeddings for fast, similarity-based search.
- Query System: Allows users to ask questions and get relevant answers directly from the PDFs.
- Interactive UI: Built with Streamlit for ease of use.
The following technologies and libraries are used in this project:
- Programming Language: Python
- Framework: Streamlit
- Libraries:
langchainfor document processingchromadbfor vector storagesentence-transformersfor generating embeddingsPyPDF2for PDF text extractionfaiss-cpufor fast vector similarity search (optional alternative to Chroma)transformersfor advanced NLP taskstorchfor deep learning support


