Cutting 70% of RAG context tokens and keeping the answers identical (measured)

Automated excerpt

Your RAG pipeline retrieves 12 chunks because the retrieval score said "maybe". On September 29, OpenAI launched the Decisions API built on Luna, and on September 15, TypeSafe launched Jev. Zero answer-quality loss on SQuAD (exact match: 0. 345 vs 0. 345) 94. 5% of gold documents retained on HotpotQA One principle drives the design: delete, do not rewrite.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.