It is these kind of videos we all need when we begin working on anything new! I've come across many videos describing how to work with Vertex AI on GCP but your series simply nails it! Great job, please continue the good work.
Hi Mike, this is excellent video. Is it possible to let the pipeline trigger automatically in case of data refresh either in google big query or in the source csv file?
Definitely! While the video shows BQ, it is also possible to use CSV in cloud storage. Here is a link that will help: cloud.google.com/vertex-ai/docs/tabular-data/classification-regression/prepare-data#import-source
@@statmike-channel I would like to see a video on building a complete pipeline of fetching data from an api and storing it in big query and using that data to train the model and deploying it to an endpoint. Hopefully you will make one.
GREAT WORK ! Thanks for this amazing video. Can we have a video with (MLOps level 2: CI/CD pipeline automation included "Vertex AI Feature Store") please ?
Great suggestion! I am really working hard on the 05 series with TensorFlow workflows that will get into these details. The content is evolving on the GitHub repo now and will turn into videos this Fall!
Hello, Im liking the serie coming from mlops engineer fammiliar w/ kubeflow it's a bit easy to catch up. But I'm not sure if it's an error from me, but the Q&A part look redundant we had the same questions and answers in the last videos ^^' (what's the secret about that?).
I am sorry this is giving you trouble. In this step the service account is being provided that will run the pipeline job. Depending on how you authenticated to the notebook it may think it is a different account than the service account, such as your account. In that case you might need act-as permission for the service account. This may be easier to help troubleshoot using the Issues tab on the GitHub repository. Here is a link that mentions it: cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform.PipelineJob#google_cloud_aiplatform_PipelineJob_run
It's my favorite theorem - the probability of event based on prior knowledge of conditions for the event. More to come on this in future videos (eventually!). Thank you for asking. en.wikipedia.org/wiki/Bayes%27_theorem
![End-To-End: Pipeline Orchestration (KFP) - AutoML in Vertex AI for ML Operations [notebook 02c]](/img/logo.svg){kind=logo}
