News for hackers. Stuff that matters.
Re:Ask HN: How do you manage knowledge you accumulate as a d... by vunderba on Wednesday March 25, 2026 @10:13AM (#47517626)
> Notion, Obsidian, plain files, GitHub wikis, Confluence — all have the same issue: search is keyword-based and only works if you remember exactly what you wrote.

My Obsidian markdown notes are continuously indexed into a private Qdrant vector database (segmented on sectional headings). I also have a local Gemma3 LLM which takes any given markdown note and generates a series of theoretical questions that could be answered by the note.

Embeddings are created for those and placed into the vector database as well to create more valuable linkage. Lots of others probably use a similar combination of keyword, semantic, and RAG to alleviate this issue as well.

Re:Ask HN: How do you manage knowledge you accumulate as a d... by stranger90 on Thursday March 26, 2026 @04:30AM (#47527942)
Already building a vector search stack (Qdrant + embeddings + RAG) and clearly invested in the problem, but no indication they're experiencing performance pain or actively shopping for managed solutions. if you want to check (Rivestack.io)