Ingest documents as vector embeddings for semantic search across multi-project workspaces.
npx skills add https://github.com/mindmorass/reflex --skill rag-builder
Please help me install this Agent Skill. Skill: rag-builder Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/rag-builder Command: npx skills add https://github.com/mindmorass/reflex --skill rag-builder
This Skill enables teams to build Retrieval-Augmented Generation pipelines by indexing documents as vector embeddings and enabling fast semantic search across multiple projects.
Start a Qdrant vector store locally, install dependencies, and run the MCP-based rag server to ingest and search documents.
High-intent search queries and answers about installing and using this skill.
Semantic search with vector embeddings indexes documents as numerical representations in a vector store, enabling fast retrieval of contextually relevant passages across projects. This Skill ingests documents, chunks them, and stores embeddings in Qdrant for multi-project isolation and fast retrieval.
A RAG pipeline requires a vector store like Qdrant, an embedding model such as SentenceTransformer, and an MCP-style server exposing ingest and search tools. This Skill provides the server and ingestion logic; you start Qdrant locally and install dependencies to begin indexing documents.
Yes. Vector databases like Qdrant store chunked documents as embeddings, enabling fast semantic search across documentation, notes, and code snippets. This Skill isolates projects within a single vector store and retrieves relevant passages with metadata during coding or brainstorming sessions.
Semantic search understands meaning and context, retrieving passages conceptually related to your query, whereas keyword search matches exact terms. Vector embeddings capture document semantics, letting you find relevant passages even when query wording differs from stored text.
After ingestion, you perform semantic search by submitting queries; the MCP-based server embeds your query and returns relevant passages ranked by similarity. Results include metadata, enabling you to trace retrieved content back to source projects and documents.
Yes. This Skill scales to documentation-heavy workflows and team knowledge bases by supporting per-project isolation within a single vector store, enabling centralized indexing while maintaining project boundaries and fast retrieval for collaborative teams.
patricio0312revConfigure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.
vasilyu1983Design and implement RAG retrieval systems with hybrid search and reranking.
JhabbigSelect embedding models and chunking strategies for semantic retrieval pipelines.
zilliztechCombine BM25 keyword matching with vector semantic similarity in Milvus.
