cosmosdb-vector-search

Azure Cosmos DB Vector Search

Best practices for configuring and using vector search in Azure Cosmos DB for AI-powered semantic search and RAG.

When to Apply

Reference these guidelines when:

• Enabling vector search on a Cosmos DB account
• Defining vector embedding policies
• Choosing vector index types (flat, quantizedFlat, diskANN)
• Writing vector similarity queries
• Implementing RAG patterns with Cosmos DB

Rules

• vector-enable-feature - Enable vector search on the account
• vector-embedding-policy - Define vector embedding policy
• vector-index-type - Configure vector indexes in indexing policy
• vector-normalize-embeddings - Normalize embeddings for cosine similarity
• vector-distance-query - Use VectorDistance for similarity search
• vector-repository-pattern - Implement repository pattern for vector search

Full Compiled Document

For all rules expanded: AGENTS.md