In a previous blog post, we built a simple retrieval pipeline where we chunked the documentation, embedded the text, and queried PostgreSQL with vector similarity to find relevant passages. Then in the most recent post, we shifted gears and focused on the ingestion side and looked at extraction of facets such as version, operating system, document type, and component, and stored them alongside...
In my previous blog post, we built the simplest possible Retrieval Augmented Generation (RAG) pipeline inside PostgreSQL. We embedded our manuals, stored those vectors in a table, ran a similarity search, and handed the top 5 results straight to a Large Language Model. The result was encouraging, we could already see the model drawing on our content rather than inventing information. But as with...
How do you turn a jumble of vector embeddings into clear, human-readable answers? In this post, we walk through the journey from raw embeddings to precise, context-aware responses—bridging the gap between data and understanding.
