RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One topic. Every takeSeek and you shall find

Reading up on rag

2 deep · digging since jan 18

  • softwaredoug.com favicon
    Agentic search models

    Smaller, domain-tuned LLMs trained specifically for search orchestration can replace complex monolithic retrieval pipelines by intelligently controlling simpler retrieval primitives.

  • news.ycombinator.com favicon
    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.