Locate past conversations and decisions in an Obsidian Vault using hybrid search.
npx skills add https://github.com/opencodos/opencodos --skill qmd-opencodos
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/opencodos/opencodos/tree/main/skills/QMD Command: npx skills add https://github.com/opencodos/opencodos --skill qmd-opencodos
Locates and retrieves past conversations, decisions, and context stored in the Obsidian Vault, enabling faster knowledge discovery and decision tracing.
Index your Obsidian Vault with qmd embed and start your first search with qmd_query.
High-intent search queries and answers about installing and using this skill.
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.
XSpoonAiIndex local notes with vector embeddings for offline semantic search.
timkraseSearch an Obsidian vault with BM25, vector, and reranked hybrid queries.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
