Actions14
- Chat Actions
- Image Actions
- Video Actions
- Agent Actions
- Audio Actions
- Tools Actions
Tools → OCR
AI-generatedSummary
Extracts printed text and layout blocks from an image using Qiniu AI OCR, accepting either an image URL or binary property data.
Inputs
- imageUrl — URL of the image to analyze. If omitted, text is extracted from the binary property specified by binaryPropertyName.
- binaryPropertyName — Name of the binary property containing the image data, used when imageUrl is not provided.
Output shape
object
Returns the extracted text, OCR layout blocks, and the raw API response.