Index and search markdown documents with BM25, vector search, and LLM reranking.
npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill qmd-ldzhhxx
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/ldzhhxx/Hermes_offline_v2/tree/main/hermes-agent/optional-skills/research/qmd Command: npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill qmd-ldzhhxx
This Skill empowers users to locally search, index, and manage personal knowledge bases, documents, and notes efficiently, reducing reliance on cloud-based services.
Index your local knowledge base with qmd collection add /path/to/knowledge-base --name knowledge-base. Once indexed, search within your knowledge base using qmd query 'keyword'.
High-intent search queries and answers about installing and using this skill.
You can index and search markdown documents locally using a hybrid search engine that combines BM25 keyword search, semantic vector search, and LLM reranking to find precise results within your personal knowledge base.
Hybrid search for personal knowledge bases combines BM25 keyword matching with semantic vector search and LLM reranking. This approach indexes local markdown and text documents to deliver precise query results without cloud dependency.
Yes, you need Node.js version 22 or higher and sqlite with extension support to index local text documents. Currently, sqlite extension support is available only on macOS for this local semantic search setup.
Yes, the local document indexing tool supports native MCP integration with Hermes Agent. This allows you to handle search queries seamlessly across your indexed markdown notes and meeting transcripts within the agent environment.
To search your local knowledge base, first index a directory using the collection add command with a specified path and name. Once indexed, you can query the collection directly using your target keywords to retrieve relevant documents.
Yes, a key limitation is that sqlite extension support is currently restricted to macOS only. Users on other operating systems cannot utilize the local knowledge base search functionality until sqlite extension compatibility is expanded.
peteromalletIndex and search local markdown and text documents with hybrid retrieval.
eddieluengSearch local markdown and text collections with hybrid retrieval and reranking.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
zerwizSearch local knowledge bases with hybrid BM25 and vector retrieval.
