Vector Database
5 posts tagged vector-database. clear filter
- 13Vector databasesday 25 · One Concept a Day — The AI-Era Engineer's Glossary
You'll learn what a vector database stores, how it finds results through chunking, embedding, indexing and querying, where it fits in an agent stack, and why live code needs grep, call graphs and freshness checks.
- 20Why swapping BM25 for a vector DB can silently lower recallday 16 · Data & Retrieval Engineering in 30 Days
A vector DB looked like an obvious upgrade until the numbers came back, and by then the agent had been quietly answering from the wrong documents for weeks.
- 18How RAG cites deleted documents when the index isn't kept freshday 13 · LLM Engineering in 30 Days
An agent confidently quoted a policy that had been deleted days earlier, and every component in the pipeline checked out fine — which is exactly why the real bug was so easy to miss.
- 14How bad chunking breaks retrieval before embeddings runday 10 · LLM Engineering in 30 Days
The answer your user needed didn't get lost in search — it got cut in half before your embedding model ever laid eyes on it, and there's a 20-minute check that proves it.
- 13When you don't need a vector database like Pineconeday 9 · LLM Engineering in 30 Days
A 10-minute audit of your actual query pattern — recall, corpus size, filters, writes — will tell you whether you need Pinecone or just Postgres, and for most RAG features the honest answer isn't the one every stack diagram assumes.