About 4k internal support pages, text embedding 3 large, pgvector. I was on 400 token chunks with 50 overlap and answers kept missing context, so I moved to 1500 with 200 overlap. Now the top 5 for almost any question…
I wrote 30 questions with expected answers, I score them myself, and every change I make lands somewhere between 20 and 24 correct. Chunk size, reranker on or off, a different prompt — all within that range. Either…
Sanity checking before I build on this. "How do I reset my password" against a paragraph about our office move scores 0.86. A genuinely relevant paragraph scores 0.89. That is a three point gap between right and…
1536 dim embeddings, cosine, ivfflat index created back when the table had maybe 20k rows. We are at 820k now and the same query that used to be 40ms is 3.1s at p95. Nothing about the query changed. 4 vCPU / 16 GB…
Internal knowledge base, 12k documents, pure vector search on pgvector. Answers are right maybe two thirds of the time and the failures are usually "it retrieved something adjacent". I have budget for one of these this…
Equipment manuals, roughly 300 pages each, 40 of them. Numbered sections and subsections, plenty of tables, some two column pages. Answers need to be precise because people are following procedures. Is heading based…