Topic

Retrieval Quality

Chunking, hybrid search, reranking, and query understanding — the levers that decide whether the right context shows up.

Why Tables Are the #1 Silent Failure in Production RAG (and How I Fixed Mine)

Tables break RAG because flattening them destroys row/column relationships; keep them as HTML and attach headers to every row to fix it.

When RAG breaks, the model usually isn't the problem — retrieval is, about 73% of the time. Here's the real failure map and what to fix first.

Vector search misses exact terms like SKUs and error codes because embeddings blur rare tokens; a sparse channel restores exact-match signal.

Attach structural, content, and contextual metadata to chunks, then use it for filtered multi-axis retrieval to sharpen RAG accuracy.

Matryoshka Representation Learning packs meaning into early dimensions so you can truncate one embedding to many sizes for fast, cheap retrieval.

Why you can't average keyword and vector scores — and how Reciprocal Rank Fusion combines them for an 8–15% accuracy gain.

Start at 512 tokens with light overlap, then tune by query type. A practical, benchmark-backed guide to chunk size for retrieval.

Corrective RAG inserts a retrieval evaluator between vector search and the LLM that scores documents and routes to proceed, filter, or re-retrieve.

Use structure-defined chunks first; when you must set a size, 256-512 tokens with 10-20% overlap is a sane default, then tune.