TGViewer
Hacker News Hacker News @hackernewslive · 28.5K subscribers
Post #232387 2.65K
Better Vector Search for Long Documents: Chunking Inside Manticore Search
Article, Comments
Manticoresearch Better Vector Search for Long Documents: Chunking Inside Manticore Search An embedding model reads only the first few hundred tokens of a document and silently drops the rest. Manticore Search now splits long documents for you at INSERT time: add chunk_strategy to the vector column and pick one of five strategies. No ingest pipeline…
  • 🤔 2
  • 🌭 1
Open in Telegram All posts from @hackernewslive
More from @hackernewslive
  1. Oct 2, 2026Around 2-6% of World Bank foreign aid got siphoned into crypto wallets Article, Comments
  2. Oct 2, 2026On social reality in China Article, Comments
  3. Oct 2, 2026Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers Article, Com…
  4. Oct 2, 2026Blogging with Gleam, Org-Mode and Pandoc Article, Comments
  5. Oct 2, 2026Apple Pass Designer Article, Comments
  6. Oct 2, 2026One month coding with GLM 5.3 Flash Article, Comments
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →