Store and retrieve documents in Qdrant for semantic search.
npx skills add https://github.com/mindmorass/reflex --skill qdrant-patterns
Please help me install this Agent Skill. Skill: qdrant-patterns Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/qdrant-patterns Command: npx skills add https://github.com/mindmorass/reflex --skill qdrant-patterns
This Skill provides a reusable pattern for storing and retrieving documents using Qdrant as a vector-based store, enabling persistent memory, research archives, and fast semantic search.
To begin, run a Qdrant instance, set the COLLECTION_NAME to your workspace, and begin storing and querying documents with qdrant-store and qdrant-find.
High-intent search queries and answers about installing and using this skill.
Semantic search with Qdrant stores documents as vectors, enabling retrieval by meaning rather than keyword matching. Use qdrant-store to persist documents with automatic embedding, then qdrant-find to query by natural language. This creates a fast, contextual memory for RAG workflows without manual indexing.
Yes. Qdrant provides persistent vector storage for RAG systems, maintaining long-term document memory across sessions. Configure COLLECTION_NAME for your workspace, store documents once, and retrieve relevant context on demand through semantic queries.
Large document collections benefit from vector-based storage like Qdrant, which indexes documents semantically and returns relevant results in milliseconds. Store your documents once with qdrant-store, then search by topic or question rather than exact terms.
No. qdrant-store handles embedding automatically during storage, so you only provide raw documents and a collection name. The Skill manages vectorization, leaving you to focus on querying and retrieval logic.
Qdrant offers fast semantic search optimized for large collections, with persistent storage and configurable collections for workspace isolation. It suits research archives and knowledge bases requiring high-speed contextual retrieval over traditional keyword indexing.
FAIQahmVectorize markdown textbook chapters and manage Qdrant Cloud collections.
whiteboardevRetrieve memory summaries by ID, project, or recency via the BrAIny API.
faionfaionGuide building and optimizing RAG systems with vector databases and retrieval strategies.
simplysmartaiImplement similarity search patterns with Pinecone, Qdrant, pgvector, and Weaviate.
