Seminarinhalt
Generative künstliche Intelligenz (KI) wird durch einfach zu verwendende Plattformen wie Azure KI Studio immer zugänglicher. Hier erfahren Sie, wie Sie generative KI-Anwendungen wie benutzerdefinierte Copilots erstellen, die Sprachmodelle und Prompt flow verwenden, um Ihren Benutzern einen Mehrwert zu bieten.
Programm
Plan and prepare to develop AI solutions on Azure
- Introduction
- What is AI?
- Azure AI services
- Azure AI Foundry
- Developer tools and SDKs
- Responsible AI
- Explore the model catalog
- Deploy a model to an endpoint
- Optimize model performance
- What is the Azure AI Foundry SDK?
- Work with project connections
- Create a chat client
- Understand the development lifecycle of a large language model (LLM) app
- Understand core components and explore flow types
- Explore connections and runtimes
- Explore variants and monitoring options
- Understand how to ground your language model
- Make your data searchable
- Create a RAG-based client application
- Implement RAG in a prompt flow
- Understand when to fine-tune a language model
- Prepare your data to fine-tune a chat completion model
- Explore fine-tuning language models in Azure AI Studio
- Plan a responsible generative AI solution
- Map potential harms
- Measure potential harms
- Mitigate potential harms
- Manage a responsible generative AI solution
- Assess the model performance
- Manually evaluate the performance of a model
- Automated evaluations
- Assess the performance of your generative AI apps
Zielgruppen
- Intermediate
- Data Scientist
- AI Engineer
- Azure AI services
Vorkenntnisse
Bevor Sie mit diesem Modul beginnen, sollten Sie sich mit grundlegenden KI-Konzepten und -Diensten in Azure vertraut machen.
Training vor Ort (Best Training Experience)
Training Online