Top Artificial Intelligence AI Courses from GitLab
How do GitLab’s AI courses aim to improve software development efficiency for developers?
GitLab's AI courses aim to improve software development efficiency for developers by providing practical guidance on utilizing AI features effectively5. These features, such as code suggestions, vulnerability explanations, and DevSecOps automation, streamline development processes by enhancing code quality, improving security, and accelerating deployment5. By leveraging AI, developers can complete tasks more efficiently, minimize errors, and ensure more secure software development. The courses cover a range of topics, including setting up code suggestions, transforming machine learning models into online apps, training ML models with GPU-enabled runners, and more.
What are the key learning outcomes of the "Setting Up Code Suggestions" course provided by GitLab?
The "Setting Up Code Suggestions" course provided by GitLab aims to teach developers how to use GitLab Duo Code Suggestions to enhance their coding efficiency. The key learning outcomes of this course include:
-
Understanding how to leverage AI for code completion and generation: Participants will learn how to use AI-powered tools to generate code suggestions, helping them write code more efficiently and accurately.
-
Learning to provide instant suggestions: The course will demonstrate how to use GitLab Duo Code Suggestions to provide real-time code suggestions, enabling developers to quickly identify and incorporate the best coding practices.
-
Creating code from natural language comments: Participants will learn how to use GitLab Duo Code Suggestions to generate code snippets based on natural language comments, making it easier for developers to understand and write code.
Overall, the course aims to empower developers to harness the power of AI in their coding workflows, helping them improve code quality, save time, and enhance collaboration.
How does the course on transforming ML models into online apps using the GitLab DevSecOps Platform and Vertex AI work?
The course on transforming ML models into online apps using the GitLab DevSecOps Platform and Vertex AI is designed to provide learners with practical insights on integrating ML models into web applications seamlessly12. The course demonstrates how to use GitLab and Vertex AI to deploy an AI model. It covers the process of using GitLab to orchestrate the ModelOps workload.
The course uses a simple introductory credit card fraud detection model as an example. This model is developed in Python and deployed as an application that uses an API endpoint to make predictions on whether a submitted transaction is fraudulent or not2.
To get started with the course, you need to have a Google Cloud project and a Google Cloud service account with the necessary permissions5. You also need to have a GitLab project.
The course comprises several steps, including:
- Inserting your Google Cloud Service Account credentials into your GitLab project's environment variables.
- Creating and uploading your dataset in Vertex AI.
- Structuring your CI/CD pipeline in GitLab, which includes stages for testing, training, and deploying the model.
- Training the model using a Python script. The training code fetches data from Vertex AI, processes it, trains the model, and saves the model to Google Cloud Storage.
- Deploying the trained model on Vertex AI using GitLab's CI/CD. This step involves creating an endpoint on Vertex AI and deploying the trained model there.
Throughout the course, you'll learn how to use these tools to deploy an AI model with Google Cloud's Vertex AI using GitLab to orchestrate the ModelOps workload2. By the end of the course, you should be able to transform your ML models into online apps using the GitLab DevSecOps Platform and Vertex AI.