Tag: search
All the articles with the tag "search".
-
Hybrid Search: BM25 and Embeddings Are Better Together
Pure vector search quietly fails on the exact terms, codes, and acronyms users actually type. Combining BM25 with dense retrieval, fusing the two, and paying the latency bill it costs.
-
Your RAG Is Bad Because Your Chunking Is Bad
A year into production RAG, the retrieval problems teams keep blaming on the model are almost always chunking, metadata, and document structure. Concrete fixes, with the splitting code I actually run.