An AI-powered study assistant that processes PDF documents and generates answers using Retrieval-Augmented Generation (RAG).
It extracts content from documents, converts them into embeddings, retrieves relevant information, and generates meaningful answers.
- π PDF text extraction
- π§© Text chunking
- π Semantic search using FAISS
- π€ Answer generation using LLM (Ollama/OpenAI)
- β‘ Fast and efficient retrieval system
- Python
- Sentence Transformers
- FAISS (Vector Search)
- PyMuPDF / pdfplumber
- Ollama / OpenAI
- RAG (Retrieval-Augmented Generation)
ai-study-assistant/ βββ rag_pipeline.py # Core RAG logic βββ test.py # Run and test the system βββ uploads/ # Input PDFs βββ requirements.txt # Dependencies βββ README.md # Project documentation