What is Reciprocal Rank Fusion?

kept by kotsakis oct 28

Reciprocal Rank Fusion combines multiple search rankings by weighting document positions rather than scores, using a simple formula with a constant k that robustly merges lexical and semantic search results.

Agentic search models
Smaller, domain-tuned LLMs trained specifically for search orchestration can replace complex monolithic retrieval pipelines by intelligently controlling simpler retrieval primitives.
also on #information-retrieval, #search-engine
Introducing TIN: full-text search for Postgres — PlanetScale
PlanetScale announces TIN, a Postgres full‑text search extension that outperforms existing indexes with up to 57× higher query throughput and lower latency.
also on ParadeDB, #software-engineering
Show HN: Omni – Open-source workplace search and chat, built on Postgres
Omni is a self-hosted AI agent platform that indexes workplace tools into a unified search and chat layer, using Postgres for hybrid search.
also on ParadeDB
The first search engine with fully vectorized query execution
Turbopuffer v3 will be the first search engine to adopt fully vectorized query execution, enabling strong performance on complex queries.
also on BM25, #search-engine
Production RAG: The Chunking, Retrieval, and Evaluation Strategies That Actually Work
Production RAG systems fail with naive fixed-size chunking and top-k retrieval, so the author recommends semantic chunking, hybrid search with BM25, reranking, context expansion, and a rigorous evaluation framework to improve accuracy and reliability.
also on BM25, #software-engineering