Query a RAG vector database to retrieve semantically relevant chunks and context.
npx skills add https://github.com/MichaelYagi/mcp_a2a --skill rag-search
Please help me install this Agent Skill. Skill: rag_search Source: https://github.com/MichaelYagi/mcp_a2a/tree/main/servers/rag/skills/rag_search Command: npx skills add https://github.com/MichaelYagi/mcp_a2a --skill rag-search
This skill enables fast semantic search over a RAG vector database to locate relevant chunks and contextual information, reducing manual digging through documents.
Example: Use rag_search_tool to query for a topic, such as "latest onboarding guidelines" and review the retrieved results.
High-intent search queries and answers about installing and using this skill.
Semantic search over a RAG vector database queries stored embeddings to retrieve relevant chunks and contextual information, reducing manual document digging. It uses the rag_search_tool and standard Python libraries to return ranked results.
Contextual grounding is achieved by running semantic search across a vector store to fetch semantically related chunks from multiple sources. This gathers supporting context for answers and presents concise, ranked results.
Yes, you can query embeddings using standard Python libraries alongside the rag_search_tool. This combination manages the vector store, applies semantic search, and returns ranked results across large corpora.
Semantic retrieval works by searching across a vector store to fetch semantically related chunks, effectively locating documents mentioning a specific topic across large corpora and presenting concise results.
You need the rag_search_tool and standard Python libraries to manage vector stores, query embeddings, and return ranked results. No additional external dependencies are required.
vecearBuild document embedding and retrieval pipelines for scalable semantic search.
abzhawChunk, embed, and rerank documents for retrieval-augmented generation pipelines.
zeronx798Manage vector collections and perform similarity searches with metadata filtering.
BEKO2210Search knowledge bases semantically with vector embeddings and keyword fallback.
