# Cloudflare Vectorize [[Cloudflare]] Vectorize is a globally-distributed vector database for embeddings, designed to pair with [[Cloudflare Workers AI]] for RAG (Retrieval-Augmented Generation) and semantic search workloads. Indexes store dense vectors with optional metadata; queries return the top-K nearest neighbors via cosine, Euclidean, or dot-product distance. It's the "V" in Cloudflare's AI stack: ingest text → embed with Workers AI → store in Vectorize → query at request time → augment LLM prompts. Same edge-native runtime characteristics as the rest of the platform: bound directly from a Worker, no separate connection pool, no cold starts. ## Why It Matters Building RAG without a managed vector DB means running Pinecone, Weaviate, Qdrant, or pgvector — extra infra, extra latency, extra bill. Vectorize collapses all of that into a Worker binding. For Cloudflare-native AI apps, it's the lowest-friction option. ## Common Use Cases - **Semantic search** over documents, products, code - **RAG** for chatbots and assistants (embed → retrieve → prompt) - **Recommendations** based on embedding similarity - **Deduplication** and clustering of unstructured content - **Personalization** — user-preference vectors matched against item vectors ## Limits Worth Knowing - Max vector dimensions: 1536 (covers OpenAI ada-002, BGE, most common models) - Max vectors per index: 5M (Standard), more on enterprise - Metadata filtering supported at query time - Free tier: 30M queried vector dimensions/month ## References - Vectorize home: https://developers.cloudflare.com/vectorize/ - RAG tutorial: https://developers.cloudflare.com/workers-ai/tutorials/ ## Related - [[Cloudflare]] - [[Cloudflare Workers]] - [[Cloudflare Workers AI]] - [[Cloudflare D1]] - [[Cloudflare R2]] - [[Wrangler]]