Topics / Embeddings & RAG
Embeddings & RAG
Retrieval-augmented generation. Embeddings, vector databases, and pipelines.
Why learn Embeddings & RAG?
-
Lets LLMs answer questions about your data, not just the open web.
-
The dominant pattern for AI chat products in 2026.
-
Vector search has applications well beyond chat.
-
A practical, high-impact skill for backend and AI engineers.
What you can build with Embeddings & RAG
Customer support over a knowledge base Internal "ask my docs" tools Semantic search and recommendations Multi-step agentic retrieval
Embeddings & RAG tutorials
5 articlesHand-written tutorials, ordered as a recommended learning path.
- 01 Embeddings What an embedding is, why cosine similarity works, how dimensionality and chunking choices affect retrieval, and a tiny numpy example you can run in your head.
- 02 Vector Databases Why a normal database struggles with vector search, how ANN indexes like HNSW and IVF work, and a clear comparison of pgvector, Qdrant, Pinecone, Chroma, and Weaviate so you can pick one.
- 03 Chunking Compare fixed-size, semantic, and structural chunking for RAG. Learn how to set overlap, attach metadata, and evaluate retrieval quality with real signals.
- 04 pgvector Use pgvector to run embeddings, similarity search, and hybrid retrieval inside Postgres. Schemas, indexes, and a working Python pipeline.
- 05 Pinecone Tutorial Build a working vector search pipeline with Pinecone in Python. Indexes, upserts, metadata filters, hybrid search, and patterns for production RAG.