qmd

You can search an Obsidian vault for past decisions and conversations using local semantic search. It combines BM25 keyword search, vector embeddings, and LLM reranking to retrieve relevant context across current and archived notes.

Hybrid search for local knowledge management combines BM25 keyword search, vector embeddings, and LLM reranking. This mechanism targets topic- and person-specific retrieval to provide accurate results from your indexed notes.

Yes, you can retrieve context from archived notes in an Obsidian vault. The search targets knowledge workers by enabling retrieval across both current and archived material to locate past decisions and map relationships.

The best way to index an Obsidian vault for vector search is using a local indexing command. Once indexed, you can query the vault to retrieve past conversations and decisions using semantic search.

You run semantic search on a local index within your Obsidian vault. The process relies on local BM25 keyword search and vector embeddings to locate past context, though LLM reranking may require external processing.

Standard Obsidian keyword search misses related context because it lacks semantic understanding. Using vector embeddings alongside BM25 keyword search and LLM reranking solves this by matching meaning and ranking relevant results accurately.