RAG isn't dead: it's still the cost-efficient answer for millions of documents
ashishllm · x · 2026-10-18
Responding to the claim that agents with search tools make RAG pipelines obsolete, ashishllm argues RAG remains essential at scale: for domains like law or healthcare with millions of compliance documents, feeding everything to an agent repeatedly is prohibitively expensive. Storing docs in a DB and retrieving relevant ones via cosine similarity is exactly what saves cost and time — that's the point of RAG.
More from coding & agent
- SpudStack on Grok Bot marketplace: a rigor reviewer for coding agents — alexcovo_eth · 2026-10-18
- OSS AI search XERJ hits 2,000 daily installs in 3 months, GitHub Rust #1 — alexcovo_eth · 2026-10-18
- Feeding an 1883 ornament design classic to AI yields striking structural analysis — debreuil · 2026-10-18
- Formal Verification of LLM-Generated Code: Slides from FATTW 2026 Talk — CatAstro_Piyush · 2026-10-18
- Indie dev's Qiaomu Obsidian plugin suite tops 20,000 downloads, Agent plugin surging — vista8 · 2026-10-18
- Zeno's paradox, agent edition: Sol does half the task, then writes 'gates' reports — max_paperclips · 2026-10-18