Skip to main content
The vlmrun generate command extracts structured data from files using pre-defined domains.

​
Image Generation

vlmrun generate image photo.jpg --domain document.invoice
Argument/OptionDescription
IMAGEPath to the input image (required)
--domainDomain to use for generation, e.g. document.invoice (required)

​
Document Generation

vlmrun generate document report.pdf --domain document.form
Argument/OptionDescription
PATHPath to the document file (required)
--domainDomain to use for generation, e.g. document.form (required)

​
Examples

# Extract invoice data from an image
vlmrun generate image invoice.jpg --domain document.invoice

# Parse a PDF form
vlmrun generate document form.pdf --domain document.form
For more flexible extraction with custom prompts and schemas, use vlmrun chat with skills instead of the generate command.