Skip to content

Cloud Vision Actions

Cloud Vision Actions are used to interact with the Google Cloud Vision API, enabling text recognition and extraction from images.

Actions

cloud_vision.image_to_text

Extracts text from an image using the Google Cloud Vision API.

Parameters:

image_path – Path of the image file to be processed.

credentials_path – Path of the Google Cloud Vision credentials file (.json).

Return:

text_boxes – Dictionary containing detected text as keys and their bounding box coordinates as values, in the format: 

"text": ((x1, y1), (x2, y2))

where (x1, y1) is the top-left coordinate and (x2, y2) is the bottom-right coordinate of the text area.

Exceptions:
  • ConnectionException – Raised if the connection to the Google Cloud Vision API fails or the credentials are invalid.
  • ImageNotFoundException – Raised if the provided image file cannot be found.