I am just starting to use Vision API by Google, the end goal being able to use it for pdfs in the future. I was watching a video and writing out the code which is the code example provided by Google. Even before getting any results, I had many errors with the ImageAnnotator() (it being not under the types module), Image()(not being under the vision library) and Label Detection (not being under vision library). Although I solved the error for ImageAnnotatorClient() and the code runs on visual code, the other two errors still persist and the code doesn’t work on the windows power shell as shown below.
Powershell result after execution of the python file.
The visual code errors I found which doesn’t stop from giving the results in the terminal shown under the image.
This shows the results of the image that I wanted to detect.
Since I just began to use google cloud platform and I am not sure what are the ways I can understand and learn the process for the project, I would be really grateful if anyone could tell me the steps to learn.
