Search the archive.

How metadata filtering actually behaves in vector search: why post-filtering breaks tenant isolation, when selective filters collapse ANN recall, and what to do.

How I pick an embedding model for retrieval: the constraints that decide it before quality does, a bake-off you can run, and the re-index nobody prices.

Scaling a worker fleet isn't adding workers to one queue. Here's how I partition pools, pick the scaling signal, and drain workers without losing jobs.

Retrieval eval is 20% metrics and 80% eval set. How I build one that survives re-indexing, which number to read at which k, and how to gate a change.

Chunking decides what your retriever can find. Here's how I split real documents — structure-first boundaries, parent-child units, and how to prove it worked.

Bad RAG retrieval is four or five distinct failures wearing one costume. Here's how I localize which one you have before changing anything.