Vector Database Management

This is your practical reference for working with Pinecone, Weaviate, and Chroma in production. It covers the full workflow from generating embeddings with OpenAI or Sentence Transformers to configuring serverless indexes, running similarity searches, and filtering with metadata. The guide includes real tradeoffs between providers (Pinecone for scale, Chroma for local dev, Weaviate for knowledge graphs) and walks through selective metadata indexing to optimize memory usage. If you're building RAG systems or semantic search and need to understand when to use cosine versus dot product metrics, or how to structure namespaces for multi-tenant applications, this gets into those specifics. Good for moving past tutorials into actual implementation decisions.

Install to Claude Code

npx -y skills add manutej/luxor-claude-marketplace --skill vector-database-management --agent claude-code