Build a Worker that embeds text with a Workers AI model and stores and queries those vectors in Vectorize for RAG retrieval

Documented steps

1. Read https://developers.cloudflare.com/vectorize/get-started/embeddings/ and the model page for whichever embedding model you choose, e.g. https://developers.cloudflare.com/workers-ai/models/bge-base-en-v1.5/ .
2. Confirm the model's output dimension from the Workers AI catalog before creating the index. '@cf/baai/bge-base-en-v1.5' outputs 768 dimensions with a 512-token input limit; '@cf/qwen/qwen3-embedding-0.6b' outputs 1,024 dimensions with up to 4,096 input tokens; '@cf/google/embeddinggemma-300m' outputs 768.
3. Create the index with matching dimensions: npx wrangler vectorize create embeddings-index --dimensions=768 --metric=cosine
4. Configure both bindings. wrangler.toml: [ai] binding = 'AI' and [[vectorize]] binding = 'VECTORIZE' / index_name = 'embeddings-index'.
5. Chunk source documents to stay under the model's token limit before embedding; do not rely on the model to handle oversized input gracefully.
6. Generate embeddings: const modelResp = await env.AI.run('@cf/baai/bge-base-en-v1.5', { text: ['chunk one', 'chunk two'] }); modelResp.data is an array of number arrays matching modelResp.shape.
7. Upsert with source metadata so retrieved matches are usable: const vectors = modelResp.data.map((v, i) => ({ id: String(i), values: v, metadata: { text: chunks[i], source: urls[i] } })); await env.VECTORIZE.upsert(vectors);
8. At query time embed the user query with the SAME model and pooling mode, then search: const q = await env.AI.run('@cf/baai/bge-base-en-v1.5', { text: [userQuery] }); const matches = await env.VECTORIZE.query(q.data[0], { topK: 3, returnMetadata: 'all' });
9. Feed matches[].metadata.text into the generation call as retrieved context, e.g. through an AI Gateway chat-completions request.
10. Deploy with npx wrangler deploy once Workers AI and Vectorize are enabled on the account.