DP-3028: Implement Generative AI engineering with Azure Databricks

Important: This course will be available on 18/07/25

Course DP-3028: Implement Generative AI engineering with Azure Databricks

This course covers generative AI engineering on Azure Databricks, using Spark to explore, refine, evaluate, and integrate advanced language models. It teaches how to implement techniques such as recovery augmented generation (RAG) and multi-stage reasoning, as well as how to refine large language models for specific tasks and evaluate their performance. Students will also learn about responsible AI practices for deploying AI solutions and how to manage models in production using LLMOps (Large Language Model Operations) on Azure Databricks.

Level: Intermediate - Role: AI Engineer, Data Scientist - Product: Azure - Subject: Artificial Intelligence, Machine Learning

Course aimed at

This course is designed for data scientists, machine learning engineers, and other AI professionals who want to build generative AI applications with Azure Databricks. It is intended for professionals familiar with fundamental AI concepts and the Azure Databricks platform.

Objectives of the official DP-3028 course

• Introduction to Language Models (LLMs): Understanding the fundamentals of generative AI, language models, and their application in natural language processing (NLP) tasks.
• Implement RAG (Retrieval-Augmented Generation): Learn how to prepare data, perform vector searches, and apply re-ranking techniques to improve the accuracy of generated responses.
• Develop multi-stage reasoning: Use frameworks such as LangChain, LlamaIndex, Haystack, and DSPy to build complex reasoning flows.
• Fine-tuning language models: Prepare data and make fine adjustments to Azure OpenAI models for specific tasks.
• Evaluate language models: Compare traditional assessments with LLM-specific metrics, including the "LLM-as-a-judge" approach.
• Apply responsible AI principles: Identify risks, mitigate problems, and apply security tools to protect AI systems.
• Implement LLMOps: Transition from MLOps to LLMOps, manage deployments with MLflow, and use Unity Catalog for version control and model security.

Content of the official Azure Databricks DP-3028 course

Module 1 Introduction to language models in Azure Databricks

• Introduction
  
• Description of generative artificial intelligence
  
• Understanding the major linguistic models (LLM)
  
• Identifying the key components of LLM applications
  
• Using LLM for natural language processing (NLP) tasks
  
• Exercise: Exploring language models

Module 2 Implementing Augmented Recovery Generation (RAG) with Azure Databricks

• Introduction
  
• Exploring the main concepts of a RAG workflow
  
• Preparing data for RAG
  
• Searching for relevant data using the search vector
  
• Reassignment of recovered results
  
• Exercise: RAG Configuration

Module 3 Implementing multi-stage reasoning in Azure Databricks

• Introduction
  
• What are multi-stage reasoning systems?
  
• Explore LangChain
  
• LlamaIndex Exploration
  
• Explore Haystack
  
• Explore the DSPy framework
  
• Exercise: Implementing multi-phase reasoning with LangChain

Module 4: Tuning language models with Azure Databricks

• Introduction
  
• What is the adjustment?
  
• Preparing the data for adjustment
  
• Tuning an Azure OpenAI model
  
• Exercise: Tuning an Azure OpenAI model

Module 5 Language model evaluation with Azure Databricks

• Introduction
  
• Comparison of LLM and traditional ML assessments
  
• Evaluation of virtual machines and artificial intelligence systems
  
• LLM evaluation using standard metrics
  
• LLM-as-a-judge description for evaluation
  
• Exercise: Evaluation of an Azure OpenAI model

Module 6 Review of responsible AI principles for language models in Azure Databricks

• Introduction
  
• What is responsible artificial intelligence?
  
• Identify risks
  
• Problem mitigation
  
• Use of key security tools to protect artificial intelligence systems
  
• Exercise: Implementing responsible AI

Module 7 Implementing LLMOps in Azure Databricks

• Introduction
  
• Transition from traditional MLOps to LLMOps
  
• Understanding model implementations
  
• Description of MLflow implementation functionalities
  
• Using Unity Catalog to manage models
  
• Exercise: Implement LLMOps

Prerequisites

Before starting this module, you should be familiar with the fundamental concepts of artificial intelligence and Azure Databricks.

Language

• Course: English / Spanish