Intelligent model deployment and consume pipeline with DataRobot AI Cloud Platform
In this tutorial, we are focusing on the third part of the AI platform “MLOps”. We are going to cover in-depth details about the model deployment, model registry, model inference application. We will deploy models from machine learning leader boards into the MLOps pipeline and consume them in various ways i.e. API, Stream, local mode, and job workflows.
DataRobot AI Cloud is a new approach built for the demands, challenges, and opportunities of AI today. It’s a single system of record, accelerating the delivery of AI to production for every organization. All users collaborate in a unified environment built for continuous optimization across the entire AI lifecycle.
It is designed for collaboration for all users in the enterprise:
- Data Science & Analytics Experts
- IT & DevOps Teams
- Executives & Information Workers
The AI Platform has 3 main functionalities:
- Data Preparation (Make your data ready for machine learning)
- Machine Learning (AutoML, VisualML)
- MLOps (Deploy your model per your need)
Video Content with Timeline:
- Earlier or prerequisite Video Tutorial
- Visiting Model Leaderboard
- Model Deployment Options
- Model Registry
- Let’s Deploy Model
- Deploy the leader model
- Rebuild Model for Deployment
- Creating applications for Model
- Consuming application
- Deploy another Model
- Replacing Deployed Model
- Various Prediction Methods
- Prediction over CLI
- Prediction workflow (Job)
- Recap
That’s all for now.
Thank you, Please Be Good and Do Good.
