Implement Generative AI engineering with Azure Databricks (DP-3028)

Reference : DP-3028

Duration : 1 day

© AFI par Edgenda inc.

This course covers generative AI engineering on Azure Databricks, using Spark to explore, fine-tune, evaluate, and integrate advanced language models. It teaches how to implement techniques like retrieval-augmented generation (RAG) and multi-stage reasoning, as well as how to fine-tune 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.

Audience

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

Prerequisites

Before attending this course, students should have :

• Familiarity with Azure Fundamentals
• Data Science and Machine Learning Basics
• Python Programming Skills
• Understanding of Databricks
• Awareness of Generative AI Concepts

Objectives

• Design and build generative AI solutions using Azure Databricks
• Leverage foundation models and large language models (LLMs) in Databricks
• Fine-tune and deploy generative AI models on Azure Databricks
• Integrate generative AI capabilities into business applications
• Apply best practices for responsible AI and data governance

Contents

Get started with language models in Azure Databricks

• Understand Generative AI
• Understand Large Language Models (LLMs)
• Identify key components of LLM applications
• Use LLMs for Natural Language Processing (NLP) tasks
• Exercise - Explore language models
• Module assessment

• Explore the main concepts of a RAG workflow
• Prepare your data for RAG
• Find relevant data with vector search
• Rerank your retrieved results
• Exercise - Set up RAG
• Module assessment

Implement multi-stage reasoning in Azure Databricks

• What are multi-stage reasoning systems?
• Explore LangChain
• Explore LlamaIndex
• Explore Haystack
• Explore the DSPy framework
• Exercise - Implement multi-stage reasoning with LangChain
• Module assessment

Fine-tune language models with Azure Databricks

• What is fine-tuning?
• Prepare your data for fine-tuning
• Fine-tune an Azure OpenAI model
• Exercise - Fine-tune an Azure OpenAI model
• Module assessment

Evaluate language models with Azure Databricks

• Compare LLM and traditional ML evaluations
• Evaluate LLMs and AI systems
• Evaluate LLMs with standard metrics
• Describe LLM-as-a-judge for evaluation
• Exercise - Evaluate an Azure OpenAI model
• Module assessment

• What is responsible AI?
• Identify risks
• Mitigate issues
• Use key security tooling to protect your AI systems
• Exercise - Implement responsible AI
• Module assessment

• Transition from traditional MLOps to LLMOps
• Understand model deployments
• Describe MLflow deployment capabilities
• Use Unity Catalog to manage models
• Exercise - Implement LLMOps
• Module assessment