pgvector and RAG, Explained Through a Real Knowledge Workflow
A plain-English walkthrough of how Markdown knowledge pages become searchable AI context using embeddings, pgvector, HNSW, and evaluation checks.
Read storyA plain-English walkthrough of how Markdown knowledge pages become searchable AI context using embeddings, pgvector, HNSW, and evaluation checks.
Read storyWhy I used a database-backed job queue for slow product workflows, and what had to be visible to users.
Read storyWhy durable product state belongs in the database, and where Prisma should stop leaking into the app.
Read story