Skip to content
All tags

#contextual-retrieval

2 posts
ai deep-dive The RAG Techniques Compendium

Late Chunking vs Contextual Retrieval: Encode-First Zero-Cost Context vs LLM-Prefix Precision and Cost

Anthropic Contextual Retrieval uses an LLM to prefix each chunk with 50-100 tokens, cutting failure rate from 5.7% to 1.9% with rerank at ~$1.02/1M tokens; Late Chunking encodes the full 32K-window document first then mean-pools by chunk boundaries for zero extra LLM cost — the trade-off is window, latency, and update shape.

#rag#chunking#late-chunking#contextual-retrieval#embedding#retrieval
ai guide The RAG Techniques Compendium

Contextual Retrieval: Giving Every Chunk Its "What This Is About" Context

When you split a document into chunks, each chunk loses its place in the original document. Contextual Retrieval solves the isolated-chunk problem by generating a per-chunk context from the whole document and prepending it at index time.

#rag#contextual-retrieval#chunking#indexing#embedding