Index and search local files with BM25, vector embeddings, and reranking.
npx skills add https://github.com/robertwaltos/openclaw --skill qmd-robertwaltos
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/robertwaltos/openclaw/tree/main/skills/qmd Command: npx skills add https://github.com/robertwaltos/openclaw --skill qmd-robertwaltos
This Skill provides a powerful command-line interface for indexing and searching local files, enabling efficient retrieval of information.
Use qmd to add the current directory as a collection named 'my-notes'.
High-intent search queries and answers about installing and using this skill.
You can index and search local files by adding them as collections to build searchable indexes. This supports natural language queries using hybrid search combining BM25 keyword matching and vector embeddings.
Hybrid search combines BM25 keyword matching with vector embeddings and reranking to retrieve local files. This mechanism improves search accuracy by merging lexical and semantic relevance scores.
You can add a local directory as a named collection using the command line interface. Once added, the system indexes the files, enabling fast retrieval and multi-modal search queries.
Yes, integrating with Ollama is required to generate vector embeddings and perform reranking. This local integration enables the semantic vector search and hybrid query capabilities.
Using a hybrid search approach is the best way to query project documentation, combining BM25 and vector search. This ensures both exact keyword matches and semantic context are retrieved.
Yes, you can update existing collections to refresh the local file index. Updating ensures that newly added notes or modified project documentation are included in subsequent searches.
caiazzopIndex and search local files using BM25, vector embeddings, and reranking.
chenchunrunExtract MITRE ATT&CK techniques from security reports and generate Sigma rules.
CraftOS-devIndex and search local files with BM25, vector embeddings, and reranking.
an8079Implement vector search with FAISS, Milvus, Qdrant, and Weaviate databases.
