Book: + | | sits on: query shape first, retrieval pattern second. The book walks through chunking, hybrid search, reranking, and the eval methodology you'd need to make the table at the top of this post for your own corpus instead of trusting mine. If your team is having the "do we still need RAG" conversation, the chapters on query routing and recall-vs-precision tradeoffs are the ones to read first.
↗ Original-Artikel auf dev.to lesenVollständiger Original-BerichtAusführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.
Long-Context Models Killed RAG. Except for the 6 Cases Where They Made It Worse.
- ▸ The two numbers that ended the debate
- ▸ The needle-in-a-haystack chart vendors stopped showing
- ▸ Case 1: Multi-hop reasoning across distant chunks
- ▸ Case 2: Contradictory sources in the corpus
- ▸ Case 3: Recency-sensitive answers
- ▸ Case 4: Needle past the 60k mark
- ▸ Case 5: Span-grounded citation requirements
- ▸ Case 6: Structured table lookups inside PDFs
- ▸ The 3 cases where long-context actually wins
- ▸ A decision rule you can paste into your design doc
- ▸ If this was useful

SOCIAL SHARE CARD GENERATOR