qdrant

What problem does it solve?

This Skill provides comprehensive guidance for effectively utilizing Qdrant, a powerful vector database, for tasks like similarity search, RAG pipelines, and recommendation engines.

Core Features & Use Cases

• Collection Design: Expert advice on creating and configuring Qdrant collections, including vector parameters, distance metrics, and payload schemas.
• Search Patterns: Demonstrates various search techniques, from basic vector search to filtered and batch searches.
• Indexing & Performance: Details on payload indexing, quantization for memory reduction, and HNSW tuning for optimal performance.
• Driver Setup: Examples for integrating Qdrant using Python, JavaScript/TypeScript, and Go clients.
• Security & Anti-Patterns: Best practices for securing Qdrant deployments and common pitfalls to avoid.

Quick Start

Use the qdrant skill to create a new collection named 'documents' with cosine distance and a vector size of 1536.