Library · evaluation

Chunking, hybrid retrieval, and reranking

Added 2026-07-14 · Last verified 2026-07-14

Chunk along semantic boundaries and keep headings, source URL, timestamps, permissions, and neighboring relationships; chunks should be small enough to isolate an answer but large enough to preserve definitions and exceptions. Hybrid retrieval combines lexical search, which excels at exact identifiers and rare terms, with vector search for paraphrases, then a reranker scores a broader candidate set before context assembly. Evaluate retrieval separately with recall at k, ranking metrics, citation coverage, and hard negatives, and apply access filters before results reach the model.

Useful?

Read the source ↗


Source: The Agent Loop — agent-loop.xyz. Curated in the open knowledge base (CC BY 4.0).

Ask a question about this ↗