← Friday, October 2, 2026Models & trainingRelease

Cloudflare AI Search adds image embeddings and PDF OCR

blog.cloudflare.com by Gabriel Massadas et al. 5 min read Editor score 7/10

The generally available retrieval pipeline adds direct image embeddings, OCR for PDFs and support for larger files, alongside text search. Preserving visual signals as well as captions can matter for multimodal retrieval over screenshots, charts and documents.

What

Cloudflare AI Search is generally available with native image embeddings, PDF OCR, and support for larger files.

How

It embeds image pixels while retaining captions; text-only embedding models can handle image queries by converting them to text with ToMarkdown.

Why it matters

Native image retrieval preserves visual details that captions can omit, enabling image similarity and detail-focused search.

Read on blog.cloudflare.com →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.