Reading up on rag
2 deep · digging since jan 18
- Agentic search models
Smaller, domain-tuned LLMs trained specifically for search orchestration can replace complex monolithic retrieval pipelines by intelligently controlling simpler retrieval primitives.
- Ask HN: How are you doing RAG locally?
Hacker News commenters share diverse local RAG setups including vector databases, SQLite FTS5, BM25, and lightweight tools like Chroma, Qdrant, and AnythingLLM.