aiqbench takeAI Products

Cloudflare's general availability of AI Search marks a significant shift toward native multimodal retrieval, moving beyond naive caption-based search to direct pixel embedding for visual data. By integrating OCR for PDFs and leveraging Matryoshka Representation Learning, the service now efficiently handles rich visual details without sacrificing storage or speed. This evolution allows developers to build more robust search pipelines that understand both textual context and fine-grained image content across various chat models.

Sources coveringCloudflare Blog, The Quantum Insider, Latent Space, arXiv

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

AI Search is now generally available

Cloudflare BlogOctober 1, 20266 min read

AI Search is now generally available. It embeds image pixels directly for visual search, runs optical character recognition on scanned PDFs, accepts files up to 10 MiB, and works with any chat model. Here's what's new and how pricing works.

Cloudflare’s AI Search combines Workers AI, Vectorize, R2, and Browser Run into a fully managed index and retrieval pipeline. Since we launched AI Search over a year ago, we’ve seen developers use it to power a wide range of search use cases, from searching internal documentation to powering search for their websites. We use AI Search ourselves to power search on our own blog and developer docs. Starting today, AI Search is generally available. And as part of it, we've expanded and improved our support for multimodal formats beyond text, adding native image embeddings, optical character recognition (OCR) for PDFs, and support for larger files. As part of general availability, we’ll start billing…

Excerpt shown under the publisher's RSS terms · 113 words · full text and figures are on the publisher's site

Read at Cloudflare Blog ↗Ask about this article