Reading a receipt from a photo

Feed an image to a vision model and get the receipt’s items back as JSON.

Intermediate5 min

In this lesson

  • Image-typed inputs
  • Asking for structured output

Build it yourself

This workflow is created in your account and opened in the editor, where you can change and run it.

The nodes in this workflow

Receipt photo

photo

Type: image. Chat shows an attach button for it.

Instruction (locked)

instruction

A fixed extraction instruction.

Language model

Gemini Flash

A vision model: it sees both the image and the instruction.

Items

items

Returns the result under this key in the API response and in chat.