# Embedding-Based Selection: The Most Practical Way to Discard Irrelevant Context

> Source: https://sukruyusufkaya.com/en/learn/token-ekonomisi/embedding-based-selection-context-pruning
> Updated: 2026-05-14T14:44:13.392Z
> Category: Token Ekonomisi & LLM Cost Optimization
> Module: Module 6: Prompt Compression
**TLDR:** In RAG, most retrieved chunks (~50-70%) don't actually contribute to the answer. Discarding question-irrelevant parts via embedding similarity saves 50-80% tokens. This lesson covers implementation, threshold selection, and validation with LLM-as-judge.