AI Fundamentals

Contextual Compression

A RAG technique that summarizes or filters retrieved chunks before feeding them to the generation model, reducing token count while preserving relevance. Common technique for long-context workloads where naive retrieval overflows the context window.

Related terms

Retrieval-Augmented Generation (RAG)
A pattern where an LLM answers a query by first retrieving relevant documents from an external corpus (typically via a vector database or hybrid search) and injecting them into the prompt as grounding context. RAG addresses freshness and factual grounding without model retraining.

Framework dimensions

Free tools

LLM Model Comparison

Whitepapers

LLM Cost Optimization Patterns

Next steps

Take the assessment— See where you stand

Where this fits

Contextual Compression is part of the AI Fundamentals vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.