npx claudepluginhub itmediatech/rag-cli --plugin rag-cliThis skill uses the workspace's default tool permissions.
Query your local document knowledge base using semantic search and get AI-powered answers.
Builds RAG systems for LLM apps with vector databases, embeddings, semantic search, and reranking. Use for document Q&A, grounded chatbots, and reducing hallucinations.
Build RAG systems for LLM apps using vector databases, embeddings, and retrieval strategies. Use for document Q&A, grounded chatbots, and semantic search.
Guides qi CLI for local knowledge search: init/index documents to SQLite, BM25/hybrid/vector search, RAG Q&A with citations using Ollama/OpenAI.
Share bugs, ideas, or general feedback.
Query your local document knowledge base using semantic search and get AI-powered answers.
This skill enables RAG (Retrieval-Augmented Generation) queries against your locally indexed documents. It uses semantic search to find relevant documents and generates answers using Claude Haiku.
/skill rag-retrieval "How to configure the API?"
query (required): Your question or search query--top-k (optional): Number of documents to retrieve (default: 5)--threshold (optional): Minimum similarity score (default: 0.7)--mode (optional): Search mode - "hybrid", "vector", or "keyword" (default: "hybrid")/skill rag-retrieval "What is the authentication process?"
/skill rag-retrieval "How to handle errors?" --top-k 10
/skill rag-retrieval "API rate limits" --mode vector
The skill uses the following configuration from config/default.yaml:
retrieval.top_k: Default number of documents to retrieveretrieval.hybrid_ratio: Balance between vector and keyword search (0.7 = 70% vector)claude.model: LLM model for response generationclaude.max_tokens: Maximum response lengthTypical latencies:
data/vectors/python scripts/index.py --input data/documents--threshold 0.5python -m src.monitoring.tcp_serverlogs/rag_cli.log