Google Vision API label detection not working error: 'str' object has no attribute before request

Question

I am trying to use the Google Vision API to read the labels for a image.

I am executing this on a Google Compute Engine instance with access to all Cloud APIs. And I am using a service account for authentication

I keep getting the following error

This the code I am executing

import io
#from google.cloud import storage
#from google.cloud.vision_v1 import ImageAnnotatorClient
from google.oauth2 import service_account
# using old version of API

from google.cloud import vision
from google.cloud.vision import types


image_client = vision.ImageAnnotatorClient(credentials='credentials.json')


with io.open('/home/username/instagram-ml/userbucket/images/test_image.jpg','rb') as image_file:
    content = image_file.read()

image = types.Image(content=content)
#
image_response = image_client.label_detection(image =image)

labels = image_response.label_annotations

Up until line

image_response = image_client.label_detection(image =image)

Everything works fine and I get no authentication issues. But when I execute the above line I suddenly get this error.

Pretty much following the instructions on this page

Not very sure what is going wrong

Answer 1

You provide the client with a string (filename?) as credentials, but as specified in the docs, the credential argument, if passed, should be an instance of Credentials or one of its subclasses.