Blog
View all seriesSearch every published post and filter by labels.
Filter By Labels
Showing 5 of 5 posts
Befriending Vector Databases - Part 5
Part 5: Build a Local pgVector Tool
Finish the series by building a tiny local semantic search tool with Postgres, pgVector, embeddings, and a command-line query loop.
Befriending Vector Databases - Part 1
Part 1: What Is a Vector Database and What Options Are Available?
A practical overview of vector databases, why they matter for AI retrieval, and where leading options shine.
Befriending Vector Databases - Part 2
Part 2: Vector Database Concepts - Embeddings: Turning Meaning Into Something Machines Can Search
Embeddings turn text, code, and media into vectors you can search by meaning — plus how model choice and chunking quietly make or break retrieval.
Befriending Vector Databases - Part 3
Part 3: Vectors And Similarity Search: How Machines Find “Close Enough”
A practical guide to similarity search: vectors, distance metrics, ANN indexes, recall/latency tradeoffs, filtering, hybrid search, and reranking.
Befriending Vector Databases - Part 4
Part 4: How Vector Indexes Work Internally: HNSW, IVF, PQ, And The Algorithms Behind Them
A hands-on mental model for vector indexing: why brute force fails, how HNSW and IVF work, what PQ compresses, and which knobs matter in real databases.