Building a Document AI Pipeline with Google CloudAcessar o laboratório
The graphical text editor was not working, loading in a infinite loop and causing me a lot of problèm
The step to get the token ID is presented later on than it is introduced, and I found this somewhat confusing. Besides that, the lab is well explained and easy to follow.
I could not finish it because BigQuery would not find my tables "in the US location" even if my project was created in the US region
Getting the TOKEN is a little bit confusing. I think that you should warn the reader, while explaining the token thing, that there are further instructions ahead in the document to get the token. Otherwise one thinks that you have to "read" the URL from the screenshot.
Some steps were confusing
I would have liked to know how to train a model for 'entity extraction', instead of how to use it. Giving two stars for demo, which wasn't working following blog https://cloud.google.com/blog/products/ai-machine-learning/building-a-document-understanding-pipeline-with-google-cloud
After the initial checkpoint, and on token generation, the instruction wasn't clear and support couldn't resolve on time... I don't think this is very helpful for people who want to really learn Document AI.