cloudflare-vectorize

Complete implementation guide for Cloudflare Vectorize - a globally distributed vector database for building semantic search, RAG (Retrieval Augmented Generation), and AI-powered applications with Cloudflare Workers. Status : Production Ready ✅ Last Updated : 2026-01-21 Dependencies : cloudflare-worker-base (for Worker setup), cloudflare-workers-ai (for embeddings) Latest Versions : wrangler@4.59.3, @cloudflare/workers-types@4.20260109.0 Token Savings : ~70% Errors Prevented : 14 Dev Time Saved : ~4 hours IMPORTANT : Vectorize V2 became GA in September 2024 with significant breaking changes. Performance Improvements : Breaking API Changes : Async Mutations - All mutations now asynchronous: returnMetadata Parameter - Boolean → String enum: Metadata Indexes Required Before Insert : V1 Deprecation Timeline : Wrangler Version Required : Why : Metadata indexes MUST exist before vectors are inserted. Vectors added before a metadata index was created won't be filterable on that property. wrangler.jsonc : Vectorize V2 supports advanced metadata filtering with range queries: Low Cardinality (Good for $eq filters) : High Cardinality (Avoid in range queries) : Current Limit : 1536 dimensions per vector Source : GitHub Issue #8729 Supported Embedding Models : Unsupported Models (>1536 dimensions): Workaround : Use dimensionality reduction (e.g., PCA) to compress embeddings to 1536 or...