From qdrant
Guides Qdrant deployment selection: local mode for prototyping, Docker/self-hosted for control, Cloud for zero-ops production, EDGE for lowest latency.
npx claudepluginhub qdrant/skills --plugin qdrantThis skill uses the workspace's default tool permissions.
Start with what you need: managed ops or full control? Network latency acceptable or not? Production or prototyping? The answer narrows to one of four options.
Guides Qdrant cluster scaling decisions for data volume, query throughput, latency, and query volume. Use for node count, sharding, vertical/horizontal scaling, or capacity issues.
Guides vector database selection for embeddings and semantic search, compares managed options like Pinecone and self-hosted like pgvector/Milvus, explains ANN algorithms like HNSW.
Integrates Qdrant vector database with LangChain4j in Java/Spring Boot apps for embedding storage, similarity search, and vector management in RAG, semantic search, or recommendations.
Share bugs, ideas, or general feedback.
Start with what you need: managed ops or full control? Network latency acceptable or not? Production or prototyping? The answer narrows to one of four options.
Use when: building a prototype, running tests, CI/CD pipelines, or learning Qdrant.
Use when: you need full control over infrastructure, data residency, or custom configuration.
Use when: you want managed infrastructure with zero-downtime updates, automatic backups, and resharding without operating clusters yourself.
/sys_metrics, managed resharding, pre-configured alertsUse when: network round-trip to a server is unacceptable. Edge devices, in-process search, or latency-critical applications.