This repo is my personal playground for learning Retrieval-Augmented Generation (RAG).🧩
Currently implemented:
- 🤗 HuggingFace models for embeddings / LLMs
- 🗂️ PyPDFLoader for document ingestion
- ⚡ FAISS as an alternative vector search backend
- 🗄️ ChromaDB for vector storage & retrieval
🎯I’ll be updating it as I explore new tools, techniques, and best practices. The goal is to experiment with different pipelines and keep improving my understanding of RAG step by step.