Vector Database Masterclass
A course that teaches vector databases, embeddings and retrieval-augmented generation from fundamentals to production, working through ChromaDB, Pinecone and LangChain in runnable Python scripts.
Vector Database Masterclass is a course covering vector databases, embeddings and RAG pipelines, from basic concepts through to production concerns such as chunking strategy and hybrid search. It is organized as a set of Python scripts and notebooks rather than a single narrative, grouped by topic: ChromaDB basics and persistence, raw embeddings, a hand-written RAG pipeline, the same pipeline with LangChain, and a Pinecone-backed version.
A chunking section compares semantic chunking against a recursive character splitter, and a hybrid-search section combines BM25 keyword search with vector search using weighted reciprocal rank fusion. Learners set up a Python virtual environment, install dependencies, and supply their own OpenAI and Pinecone API keys through an environment file before running the scripts.