Index and search local files with BM25, vector embeddings, and reranking.
npx skills add https://github.com/brianwan19801015/labopenclaw --skill qmd-brianwan19801015
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/brianwan19801015/labopenclaw/tree/main/skills/qmd Command: npx skills add https://github.com/brianwan19801015/labopenclaw --skill qmd-brianwan19801015
This Skill provides a command-line interface for indexing and searching local files, offering advanced capabilities beyond simple text search.
Use qmd to search for 'AI agent development' within your indexed documents.
High-intent search queries and answers about installing and using this skill.
BM25 search is a keyword-based algorithm that ranks local files based on term frequency and relevance. It enables efficient information retrieval from local document collections via command-line operations, providing fast text matching without requiring external embedding models.
Ollama is optionally required to enable vector embeddings and reranking functionalities for your local file indexing. The core binary supports BM25 keyword search independently, but semantic and hybrid search methods require the Ollama integration to process natural language queries.
The best way to index markdown files is using the command-line interface to create a local index. Once indexed, you can execute hybrid search combining BM25 keyword matching and vector semantic retrieval to quickly find information across your project's document collections.
Yes, you can fetch specific documents or snippets with surrounding context from your local indexes. The command-line tool facilitates efficient document retrieval, allowing you to extract targeted information from your indexed local files after running a search.
Use hybrid search when natural language queries lack exact keywords, combining BM25 term matching with vector semantic retrieval. Use BM25 alone for precise keyword lookups in local files, avoiding the overhead of generating vector embeddings and reranking via Ollama.
CraftOS-devIndex and search local files with BM25, vector embeddings, and reranking.
chenchunrunExtract MITRE ATT&CK techniques from security reports and generate Sigma rules.
JFrangelOptimize RAG pipelines with semantic chunking, embedding selection, and vector database configuration.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
