Azure OpenAI Service & Generative AI Training

Build production-ready generative AI applications with Azure OpenAI Service in this hands-on 3-day training. Learn to work with GPT models, embeddings, function calling, and the Assistants API while implementing enterprise patterns for rate limiting, token management, cost optimization, and content safety.

Training Details


Duration	3 days (24 hours)
Level	Intermediate
Delivery	In-person, Live online, Hybrid

Who Is This For?

Software developers building generative AI applications
Backend engineers integrating Azure OpenAI into existing systems
AI engineers designing production GenAI solutions
Technical architects planning enterprise GenAI deployments
DevOps engineers managing GenAI infrastructure on Azure

Learning Outcomes

After completing this training, you’ll be able to:

Deploy and configure Azure OpenAI Service models for production use
Engineer effective prompts with system messages and few-shot patterns
Implement embeddings and vector search for semantic retrieval
Build function calling and tool-use patterns for agentic applications
Design RAG architectures with Azure AI Search and Azure OpenAI
Apply enterprise patterns for cost control, rate limiting, and content safety

Detailed Agenda

Day 1: Azure OpenAI Service Fundamentals

Module 1: Azure OpenAI Service Setup and Model Deployment

Azure OpenAI Service provisioning and configuration
Model families: GPT-4o, GPT-4, GPT-3.5, and embeddings models
Deployment types: standard, provisioned throughput, and global
Quotas, rate limits, and regional availability
Hands-on: Deploy and configure Azure OpenAI models

Module 2: Prompt Engineering Best Practices

Prompt engineering principles and techniques
System prompts and persona design
Few-shot learning and chain-of-thought reasoning
Temperature, top-p, and other inference parameters
Hands-on: Engineer prompts for real-world scenarios

Module 3: Chat Completions and System Prompts

Chat completions API deep dive
Multi-turn conversation management
Token counting and context window optimization
Streaming responses and real-time output
Hands-on: Build a multi-turn chat application

Day 2: Advanced Capabilities and RAG

Module 4: Embeddings and Vector Search

Text embeddings concepts and Azure OpenAI embedding models
Vector databases and Azure AI Search vector store
Semantic search vs. keyword search vs. hybrid search
Embedding strategies for large document collections
Hands-on: Build a semantic search solution

Module 5: Function Calling and Tool Use

Function calling API and structured outputs
Defining tool schemas and handling tool responses
Parallel function calling and multi-step workflows
Building agentic applications with tool use
Hands-on: Create a function-calling application

Module 6: Assistants API and Multi-Turn Conversations

Assistants API architecture and concepts
Threads, messages, and run management
Code interpreter and file search tools
Persistent conversation state management
Hands-on: Build an assistant with code interpreter

Day 3: Enterprise Patterns and Production Deployment

Module 7: RAG Architecture with Azure AI Search

RAG design patterns and architecture decisions
Azure AI Search indexing and skillsets
Chunking strategies and document processing
Grounding and citation generation
Hands-on: Build a production RAG pipeline

Module 8: Content Filtering and Safety

Azure OpenAI content filtering system
Category filters: hate, violence, self-harm, and sexual content
Custom blocklists and prompt shields
Responsible AI monitoring and compliance
Hands-on: Configure content filtering policies

Module 9: Enterprise Patterns and Production Deployment

Rate limiting and retry strategies with exponential backoff
Token management and cost optimization techniques
Load balancing across multiple deployments
API gateway patterns with Azure API Management
Hands-on: Implement enterprise patterns for GenAI

Module 10: Deploying Generative AI Applications

Application architecture for GenAI solutions
Azure App Service and Container Apps for GenAI hosting
CI/CD pipelines for GenAI applications
Monitoring, logging, and observability
Hands-on: Deploy a GenAI application to production

Prerequisites

Basic familiarity with Azure portal and services
Programming experience in Python or JavaScript
Understanding of REST APIs and HTTP concepts
Familiarity with JSON data format

Delivery Formats

Format	Description
In-Person	On-site at your company’s location, hands-on with direct interaction
Live Online	Interactive virtual sessions with screen sharing and real-time labs
Hybrid	Combination of on-site and remote sessions, flexible scheduling

All formats include hands-on labs, course materials, reference architectures, code samples, and post-training support.