| Module 1: Introduction to Azure AI Studio |
| Microsoft Azure offers multiple services that enable developers to build amazing AI-powered solutions. Azure AI Studio brings these services together in a single unified experience for AI development on the Azure cloud platform. |
| Lessons: |
|
|
- When to use Azure AI Studio
|
|
|
- Exercise – Explore Azure AI Studio
|
- How does Azure AI Studio work
|
|
| Module 2: Explore and deploy models from the model catalog in Azure AI Studio |
| Explore the various language models that are available through the Azure AI Studio’s model catalog. Understand how to select, deploy, and test a model, and to improve its performance. |
| Lessons: |
|
|
- Improve the performance of a language model
|
- Explore the language models in the model catalog
|
- Exercise – Explore, deploy, and chat with language models
|
- Deploy a model to an endpoint
|
|
| Module 3: Get started with prompt flow to develop language model apps in the Azure AI Studio |
| Learn about how to use prompt flow to develop applications that leverage language models in the Azure AI Studio. |
| Lessons: |
|
|
- Explore variants and monitoring options
|
- Understand the development lifecycle of a large language model (LLM) app
|
- Exercise – Get started with prompt flow
|
- Understand core components and explore flow types
|
|
- Explore connections and runtimes
|
|
| Module 4: Build a RAG-based copilot solution with your own data using Azure AI Studio |
| Copilots can work alongside you to provide suggestions, generate content, or help you make decisions. Copilots use language models as a form of generative artificial intelligence (AI) and will answer your questions using the data they were trained on. To ensure a copilot retrieves information from a specific source, you can add your own data when building a copilot with the Azure AI Studio. |
| Lesson: |
|
|
- Build a copilot with prompt flow
|
- Understand how to ground your language model
|
- Exercise – Create a custom copilot that uses your own data
|
- Make your data searchable
|
|
| Module 5: Integrate a fine-tuned language model with your copilot in the Azure AI Studio |
| Train a base language model on a chat-completion task. The model catalog in the Azure AI Studio offers many open-source models that can be fine-tuned for your specific model behavior needs. |
| Lessons: |
|
|
- Explore fine-tuning language models in Azure AI Studio
|
- Understand when to fine-tune a language model
|
- Exercise – Fine-tune a foundation model
|
- Prepare your data to fine-tune a chat completion model
|
|
| Module 6: Evaluate the performance of your custom copilot in the Azure AI Studio |
| Evaluating copilots is essential to ensure your custom copilots meet user needs, provide accurate responses, and continuously improve over time. Discover how to assess and optimize the performance of your custom copilot using the tools and features available in the Azure AI Studio. |
| Lessons: |
|
|
- Assess the performance of your custom copilot
|
- Assess the model performance
|
- Exercise – Evaluate the performance of your custom copilot
|
- Manually evaluate the performance of a model
|
|
| Module 7: Responsible generative AI in AI Studio |
| Generative AI enables amazing creative solutions, but must be implemented responsibly to minimize the risk of harmful content generation. |
| Lessons: |
|
|
|
- Plan a responsible generative AI solution
|
- Operate a responsible generative AI solution
|
|
|
- Exercise – Explore content filters in Azure AI Studio
|
|
|
|
