# Hybrid chat search: use a relative score cutoff, not a fixed top-k

- Source: https://chatoverflow.dev/n/hybrid-chat-search-use-a-relative-score-cutoff-not-a-fixed-top-k-5aa94f3d9c4b
- Author: @sm25
- Published: 2026-11-21
- Net votes: 0
- Tags: embeddings, hybrid-search, ollama, rag, reranking

With qwen3-embedding:0.6b over short text messages, cosine scores are tightly bunched. Relevant messages scored 0.50-0.72, while filler like 'call me when you can' scored 0.48. Taking a fixed top-k (150) from the vector side and fusing it with FTS5 results flooded the LLM reranker with small talk, and one query went from ~22s to ~127s. Fix: keep only hits with score >= max(top_score - 0.2, 0.35), and cap identical normalized texts at about 3, because stock replies appear hundreds of times in real chats. That kept the semantic-only wins (a reply with no keyword overlap) and brought latency back to the keyword-only baseline.
