RAG & retrieval

AI & agents › RAG & retrieval · topic id ai/rag · 18 articles · generated, edit catalog.jsonl or notes/ instead

Retrieval-augmented generation, vector DBs, vectorless and file-first retrieval.

To read (18)

• GitHub: tobi/qmd
  gh-tobi-qmd · to-read · 2026-09-25 · #github-repo
• The markdown file that beat a $50M vector database — @Micheal-Lanham
  the-markdown-file-that-beat-a-50m-vector-database · to-read · 2026-04-08 · #token-cost #vectorless
• Stop chunking start reasoning how PageIndex replaces vector search with LLM driven retrieval — @pankaj_pandey
  stop-chunking-start-reasoning-how-pageindex-replaces-vector-search-wit · to-read · 2026-04-08 · #rag #vectorless
• RAG is dead before you build it try file first AI agent — @denisuraev
  rag-is-dead-before-you-build-it-try-file-first-ai-agent · to-read · 2026-04-08 · #rag #vectorless
• Vectorless RAG for agents PageIndex is why their demo works and yours needs context
  vectorless-rag-for-agents-pageindex-is-why-their-demo-works-and-yours · to-read · 2026-02-12 · #rag #vectorless
• NextGen Search - Where AI Meets OpenSearch Through MCP
  nextgen-search-where-ai-meets-opensearch-through-mcp · to-read · 2025-12-20 · #mcp
• When (Not) to Use Vector DB
  when-not-to-use-vector-db · to-read · 2025-12-18
• Building AI that actually thinks a complete guide to agentic RAG
  building-ai-that-actually-thinks-a-complete-guide-to-agentic-rag · to-read · 2025-11-29 · #rag
• Choosing our vector database why we bet on a 30 year old technology for our AI’s agentic memory
  choosing-our-vector-database-why-we-bet-on-a-30-year-old-technology-fo · to-read · 2025-11-23 · #memory
• I Deployed My RAG System to Production — 7 Things That Failed in First Week — CodeOrbit
  i-deployed-my-rag-system-to-production-7-things-that-failed-in-first-w · to-read · 2025-11-22 · #rag
• GitHub: apple/embedding-atlas
  gh-apple-embedding-atlas · to-read · 2025-11-10 · #github-repo
• RAG is not dead no chunking no vectors just vectorless to get the higher accuracy
  rag-is-not-dead-no-chunking-no-vectors-just-vectorless-to-get-the-high · to-read · 2025-10-23 · #rag #vectorless
• Optimizing RAG with the smarter indexing RAPTOR pipeline
  optimizing-rag-with-the-smarter-indexing-raptor-pipeline · to-read · 2025-09-04 · #rag
• Testing 18 RAG techniques to find the best
  testing-18-rag-techniques-to-find-the-best · to-read · 2025-03-21 · #rag
• You’re doing RAG wrong how to fix retrieval augmented generation for local LLMs
  you-re-doing-rag-wrong-how-to-fix-retrieval-augmented-generation-for-l · to-read · 2025-03-12 · #rag #local-llm
• Multi-Agentic RAG with Hugging Face Code Agents — Gabriele Sgroi, PhD
  multi-agentic-rag-with-hugging-face-code-agents · to-read · 2025-01-01 · #multi-agent #rag
• 17 (Advanced) RAG Techniques to Turn Your LLM App Prototype into a Production-Ready Solution — Dominik Polzer
  17-advanced-rag-techniques-to-turn-your-llm-app-prototype-into-a-produ · to-read · 2024-06-28 · #rag
• 12 RAG pain points and proposed solutions
  12-rag-pain-points-and-proposed-solutions · to-read · 2024-05-09 · #rag