PDF Sensei is a machine learning-powered application that allows users to upload multiple PDF documents and interactively ask questions based on their content. The app processes and extracts information from uploaded PDFs to provide context-aware answers.
Features:
Upload multiple PDF documents for analysis.
Automatically extracts and processes text from the PDFs.
Splits text into manageable chunks for efficient querying.
Uses advanced language models (**FLAN-T5 Large**) for natural language understanding.
Employs vector-based semantic search with *Instructor-XL embeddings* for accurate retrieval.
Maintains conversation history to provide context-aware answers.
GitHub repo: https://github.com/akshaychavan7/PDF-...