qdrant-vectorstore

What problem does it solve?

This Skill helps you manage semantic vector storage and retrieval for knowledge bases by interfacing with Qdrant Cloud. It handles collection creation, document embedding storage with automatic chunking, and fast semantic search for RAG chatbots, reducing manual setup and integration work.

Core Features & Use Cases

• Collection Management: Create and manage Qdrant collections with cosine similarity configuration.
• Document Storage: Automatically chunk large documents and store embeddings for efficient retrieval.
• Semantic Search: Query across stored vectors to fetch relevant chunks with relevance scores.
• Reliability: Built-in retry logic with exponential backoff and robust logging.

Quick Start

To get started, create a collection, upsert documents, and perform a search:

• Create collection: /ask Use qdrant-vectorstore to create collection "tech_docs"
• Upsert documents: /ask Use qdrant-vectorstore to upsert into "tech_docs": ["Machine learning is a subset of artificial intelligence...", "Deep learning uses neural networks..."]
• Search documents: /ask Use qdrant-vectorstore to search "tech_docs" for "neural networks"