Azure Open AI for Developers

Azure Open AI - Developing solutions with Large Language Models. Azure OpenAI Service provides access to OpenAI's powerful large language models such as ChatGPT, GPT, Codex, and Embeddings models. These models enable various natural language processing (NLP) solutions to understand, converse, and generate content. Users can access the service through REST APIs, SDKs, and Azure OpenAI Studio.

We will explore how to take advantage of large-scale, generative AI models with deep understandings of language and code to enable new reasoning and comprehension capabilities for building cutting-edge applications. We will apply these coding and language models to a variety of use cases.

The training will also explore how to detect and mitigate harmful use with built-in responsible AI and access enterprise-grade Azure security.

Audience

Software developers and engineers concerned with building, managing, and deploying AI solutions that leverage Azure Open AI services. They are familiar with C#, Python, or JavaScript and have knowledge on using REST-based APIs.

Prerequisites

• Knowledge of Microsoft Azure and ability to navigate the Azure portal
• Knowledge of either C# or Python

Course goals

By attending this course, you will gain the following skills:

• Implementing solutions for Azure Open AI Services using prompt engineering techniques, integrating your own data, creating responsible solutions and deploying them.
• Implementing solutions with Azure Prompt flow where you will learn how to streamline the entire development cycle of AI applications powered by Large Language Models (LLMs)
• Working with Azure AI Studio where you will learn how to build, evaluate, and deploy your AI solutions from end to end with Azure AI Studio
• Create and deploy end-to-end models where you will get a lot of experience with developing your own models with Azure Open AI – both REST and SDKs.
• Developing your own copilot where you will learn how to use Semantic Kernel, a lightweight open-source SDK. With Semantic Kernel, you can leverage the same AI orchestration patterns that power Microsoft 365 Copilot and Bing in your own apps

Course outline

 

Large Language Models and Azure Open AI – an introduction

In this module you will get a high-level perspective on Large Language Models (LLM), the background and the opportunities you get with Azure Open AI.

Implement solutions for Azure Open AI

In this module we will explore how to build clients with Azure Open AI – REST-based and SDKs. You will work with the following topics:

• Chat and Completions
• Prompt engineering
• Embedding and vectors with prompt engineering
• Fine-tuning with Azure Open AI.
• Knowledge mining and Retrieval Augmented Generation (RAG) in Azure AI Search. Use your own data with Prompt engineering – integrate Azure AI Search in your solution with a focus on indexing, keywords, vectors and semantic relevance.
• Responsible AI

Azure Prompt Flow

Azure Machine Learning prompt flow is a development tool designed to streamline the entire development cycle of AI applications powered by Large Language Models (LLMs) It simplifies the process of prototyping, experimenting, iterating, and deploying your AI applications.

In this module we will explore:

• An overview of Azure Prompt Flow
• Use cases and examples.
• Integrating Prompt Flow in you code
• Integrating external tools like Langchain
• Evaluating the flow
• MLOps – from use case to deployment

Azure AI Studio

Build, evaluate, and deploy your AI solutions from end to end with Azure AI Studio

• Azure AI Studio – an overview
• How to build and deploy a question and answer copilot with prompt flow in Azure AI Studio:
  1. Create an Azure AI Studio project.
  2. Deploy an Azure OpenAI model and chat with your data.
  3. Create a prompt flow from the playground.
  4. Customize prompt flow with multiple data sources.
  5. Evaluate the flow using a question and answer evaluation dataset.
  6. Deploy the flow for consumption.
• Incorporate multimodality
• Azure AI SDK. Use your favorite frameworks and editors that allow you to work in your preferred code environments with direct access to Azure AI.
• Explore cutting-edge models. Explore and test large AI models from Microsoft, Azure OpenAI, Meta, and Hugging Face to find the right one for your use case.

Create and customize end-to-end models

In this module we will explore useful Azure Open AI resources and code samples to help you get started and accelerate your technology adoption journey.

The Azure OpenAI service provides REST API access to OpenAI's powerful language models on the Azure cloud. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation. We will access the service through REST APIs, Python SDK, .NET SDK.

Build you own copilot

To help developers build their own Copilot experiences on top of AI plugins, Microsoft have released Semantic Kernel, a lightweight open-source SDK that allows you to orchestrate AI plugins. With Semantic Kernel, you can leverage the same AI orchestration patterns that power Microsoft 365 Copilot and Bing in your own apps, while still leveraging your existing development skills and investments.
In this module we will explore the possibilities.

 

Other relevant courses