What is MCP mode in QMD?

MCP mode enables the Model Context Protocol, allowing QMD to act as a standardized server that Claude and other AI tools can communicate with to access indexed data.

What is the primary function of the QMD skill?

QMD is a local search and indexing tool that allows Claude to efficiently find and retrieve information from your local files using both keyword and semantic search methods.

How do I update my search index after changing files?

You can simply run the 'qmd update' command to refresh the index with any changes made to your local files.

Does QMD require an external API for vector search?

No, QMD is designed to work with Ollama locally for embeddings and reranking, ensuring your data remains private and accessible offline.

Where are the search indexes stored on my machine?

By default, QMD stores its indexing data locally in the '~/.cache/qmd' directory of your operating system.

QMD Local Search & Indexing

Name: QMD Local Search & Indexing
Author: clawdbot

byclawdbot

•

1,921

콘텐츠 관리

Indexes and searches local files using hybrid BM25 and vector search to provide fast, private document retrieval for Claude.

소개

The QMD skill empowers Claude to efficiently navigate and query local file systems by leveraging advanced indexing techniques including BM25, vector embeddings, and reranking. By integrating with Ollama for local embeddings, it allows users to perform high-precision semantic searches across codebases or documentation without sending data to external search providers. This skill is ideal for developers managing large-scale knowledge bases or private projects where traditional keyword search is insufficient and data privacy is paramount.

주요 기능

Model Context Protocol (MCP) support for standardized tool interoperability
Granular document retrieval with support for specific line ranges and contexts
1,921 GitHub stars
Hybrid search combining BM25 keyword matching and vector-based semantic retrieval
Seamless integration with Ollama for local embedding and reranking models
Local indexing and storage for a privacy-first document management experience

사용 사례

Navigating large technical documentation repositories to find specific implementation patterns
Quickly locating relevant code snippets or context across multiple disparate project directories
Building a local Retrieval-Augmented Generation (RAG) system for private codebases

소개

주요 기능

Model Context Protocol (MCP) support for standardized tool interoperability
Granular document retrieval with support for specific line ranges and contexts
1,921 GitHub stars
Hybrid search combining BM25 keyword matching and vector-based semantic retrieval
Seamless integration with Ollama for local embedding and reranking models
Local indexing and storage for a privacy-first document management experience

사용 사례

Navigating large technical documentation repositories to find specific implementation patterns
Quickly locating relevant code snippets or context across multiple disparate project directories
Building a local Retrieval-Augmented Generation (RAG) system for private codebases