Index and search local files using BM25, vector embeddings, and reranking.
npx skills add https://github.com/caiazzop/clawdbot-personal-assistant --skill qmd-caiazzop
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/caiazzop/clawdbot-personal-assistant/tree/main/skills/qmd Command: npx skills add https://github.com/caiazzop/clawdbot-personal-assistant --skill qmd-caiazzop
This Skill provides a powerful command-line interface for indexing and searching local files, enabling efficient retrieval of information stored on your system.
Use qmd to search for 'AI assistants' within your indexed documents.
High-intent search queries and answers about installing and using this skill.
You can index and search local files using the qmd command-line interface to facilitate efficient information retrieval from local document collections. It creates indexes stored locally in the ~/.cache/qmd directory.
Hybrid search combines BM25 and vector search methods to comprehensively retrieve information from your local documents. This combined approach leverages both keyword matching and semantic embeddings for better results.
Yes, you need Ollama to perform vector search and reranking on local files. The system leverages Ollama specifically to generate vector embeddings and rerank your indexed document snippets.
The best way to retrieve specific snippets is by using the quick retrieval features of the qmd CLI. It allows you to efficiently search within your indexed local files for specific keywords or concepts.
Yes, you can use BM25 for local file indexing independently of vector embeddings. The system supports BM25, vector search, and a combined hybrid approach, giving you flexibility in retrieval methods.
Local search indexes are stored on your system in the ~/.cache/qmd directory. This allows the command-line interface to quickly access and manage your indexed document collections.
steipeteIndex local files and search them with BM25, vector, and hybrid queries.
JCE-Joshhh77Assemble end-to-end RAG pipelines with chunking, embeddings, and vector search.
SARAMALI15792Execute Python code in-browser with Pyodide for interactive exercises.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
