
Fig 1

Fig 2

Fig 3
RAG Knowledge Engine
AI-powered semantic search system for documents
Python
FAISS
Transformers
System Highlights
- >FAISS-based vector search for high-accuracy semantic retrieval
- >End-to-end RAG pipeline with PDF parsing & persistent vector storage
- >Sub-second retrieval with local LLM integration
- >65% performance improvement via optimized vector indexing