Cloudflare AI Search goes GA with multimodal embeddings, PDF OCR, billing from Nov 1
michellechen · x · 2026-10-02
Cloudflare announced general availability of AI Search, a fully managed index and retrieval pipeline combining Workers AI, Vectorize, R2, and Browser Run. New in GA: native image-pixel embeddings alongside captions for visual retrieval (using Matryoshka Representation Learning to keep embeddings compact), OCR for PDFs, and larger file support. Billing starts November 1, 2026, with a generous free tier across all Workers plans. The team is also rebuilding keyword search on top of R2.
More from Infra
- PyTorch ships TorchTPU: vLLM and SGLang now run natively on Google TPUs — PyTorch · 2026-10-02
- Lightmatter CEO on Optical Interconnect: NPO Stays, Lasers Move to 300mm Silicon CMOS — BenBajarin · 2026-10-02
- Musk: SpaceX version of VR72 may run at close to 250kW average power with Nvidia — McDonaghMatthew · 2026-10-02
- DDR5/PCIe5 is 15-20% faster for LLM pre-training, but DDR4 wins on cost per dollar — Any-Winter-4079 · 2026-10-02
- Modal makes GPU clusters generally available with one-line RDMA support — josh_wills · 2026-10-02
- Bet on bits, not history: why AI broke the old memory valuation cycle — BenBajarin · 2026-10-02