HNSW ef_search: Why Your Vector Search Misses the Right Chunk

<p>Your RAG application works perfectly with 1,000 documents. You push it to production, upload 10 million vectors, and suddenly your query latency jumps from 50ms to 5 seconds.

<!-- SC_OFF --><div class="md"><p>We spent the last year building a code indexing system and tried pretty much every retrieval approach along the way. Sharing what actually worked

<p><a class="article-body-image-wrapper"

<p>Our careers page search often felt broken. Searching for “Java” could return JavaScript roles. A misspelling could produce no results at all. Searching for “manager” could

<p>Adding full-text search to Postgres is a two-line migration. Running it in production without surprises is not. The GIN index that makes search fast also adds write

<p>Most semantic search systems don’t fail because of embeddings. They fail because of how the system is designed around them.</p> <p>When I started building a semantic search API

<p><em>A deep-dive into the latest FerresDB updates — from HNSW auto-tuning and PolarQuant compression to Point-in-Time Recovery, cross-encoder reranking, and a distributed Raft