Index local notes and transcripts for hybrid BM25 and vector search.
npx skills add https://github.com/ever-oli/io --skill qmd-ever-oli
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/ever-oli/io/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/ever-oli/io --skill qmd-ever-oli
Local knowledge bases, notes, transcripts, and documents are often scattered and hard to locate. This skill enables fast, on-device search with a hybrid retrieval pipeline to surface relevant content without cloud dependencies.
Use qmd to search your notes for "onboarding" and retrieve matching documents.
High-intent search queries and answers about installing and using this skill.
You can search local markdown notes and transcripts offline by indexing them on-device with a hybrid retrieval pipeline that combines BM25 keyword search and vector semantic similarity to surface relevant documents without cloud dependencies.
Hybrid retrieval for personal knowledge bases is a search mechanism that combines BM25 keyword matching with vector semantic search and LLM reranking to optimize retrieval quality across local document collections.
Yes, local knowledge base search supports MCP integration by exposing native tools that allow you to automate indexing and retrieval workflows across your personal documentation collections.
Yes, you can use vector similarity and BM25 keyword search together through the hybrid retrieval pipeline, which then applies LLM reranking to the combined results to deliver high-quality matches from your indexed content.
No, you do not need cloud services for vector search on your documentation. The skill performs on-device indexing and local computation for vector similarity and BM25 search, ensuring your knowledge base remains private.
The best way to find specific information across scattered local documents is to index them locally and use a hybrid search approach, leveraging BM25 and vector similarity with LLM reranking to quickly surface precise matches.
JKHeadleyIngest URLs, documents, and transcripts into a searchable knowledge base.
cpich3gRetrieve live Microsoft 365 context and generate actionable summaries from emails, meetings, documents, Teams, and people.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
InverterNetworkCreate serverless vector indexes and run hybrid search queries.
