Cloudflare RAG Demo
Workers AI + Vectorize + AI Gateway
Architecture
Your Question
→
Workers AI Embeddings
→
Vectorize (semantic search)
→
AI Gateway → Llama 3.1
→
Grounded Answer
Ask
Workers AI GPU inference?
AI Gateway fallback?
Vectorize similarity metrics?
R2 vs S3 egress costs?
Agents SDK state?