Cloud Private

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

1 day
AzureAIAzure DevOps ServicesPythonSpark

Learn generative AI engineering with Azure Databricks and Spark: RAG, multi-stage reasoning, fine-tuning and evaluating LLMs, responsible AI, and LLMOps.

Request Private Class

Register or Request Training

  • Private class for your team
  • Live expert instructor
  • Online or on‑location
  • Customizable agenda
  • Proposal turnaround within 1–2 business days
Request Proposal

Course Overview

This course covers generative AI engineering on Azure Databricks using Spark to explore, fine-tune, evaluate, and integrate advanced language models. You will learn to implement retrieval-augmented generation (RAG) and multi-stage reasoning, fine-tune large language models for specific tasks, and evaluate model performance. The course also introduces responsible AI practices and LLMOps for managing and deploying models in production on Azure Databricks.

Course Benefits

  • Understand generative AI concepts and large language models (LLMs) in Azure Databricks
  • Build LLM application components and apply LLMs to NLP tasks
  • Implement retrieval-augmented generation (RAG), including vector search and reranking
  • Implement multi-stage reasoning approaches using common frameworks
  • Prepare data for fine-tuning and fine-tune an Azure OpenAI model in Azure Databricks
  • Evaluate LLMs using standard metrics and LLM-as-a-judge techniques
  • Apply responsible AI principles, risk identification, mitigation, and security tooling
  • Implement LLMOps practices, including deployment with MLflow and model management with Unity Catalog

Delivery Methods

Private Class
Delivered for your team at your site or online.

Microsoft Certified Partner

Webucator is a Microsoft Certified Partner. This class uses official Microsoft courseware and will be delivered by a Microsoft Certified Trainer (MCT).

Microsoft Certified Partner

Course Outline

  1. Get started with language models in Azure Databricks
    1. Understand Generative AI
    2. Understand Large Language Models (LLMs)
    3. Identify key components of LLM applications
    4. Use LLMs for Natural Language Processing (NLP) tasks
  2. Implement Retrieval Augmented Generation (RAG) with Azure Databricks
    1. Explore the main concepts of a RAG workflow
    2. Prepare your data for RAG
    3. Find relevant data with vector search
    4. Rerank your retrieved results
  3. Implement multi-stage reasoning in Azure Databricks
    1. What are multi-stage reasoning systems?
    2. Explore LangChain
    3. Explore LlamaIndex
    4. Explore Haystack
    5. Explore the DSPy framework
  4. Fine-tune language models with Azure Databricks
    1. What is fine-tuning?
    2. Prepare your data for fine-tuning
    3. Fine-tune an Azure OpenAI model
  5. Evaluate language models with Azure Databricks
    1. Explore LLM evaluation
    2. Evaluate LLMs and AI systems
    3. Evaluate LLMs with standard metrics
    4. Describe LLM-as-a-judge for evaluation
  6. Review responsible AI principles for language models in Azure Databricks
    1. What is responsible AI?
    2. Identify risks
    3. Mitigate issues
    4. Use key security tooling to protect your AI systems
  7. Implement LLMOps in Azure Databricks
    1. Transition from traditional MLOps to LLMOps
    2. Understand model deployments
    3. Describe MLflow deployment capabilities
    4. Use Unity Catalog to manage models

Class Materials

Each student receives a comprehensive set of materials, including course notes and all class examples.

Class Prerequisites

Experience in the following is required for this Azure class:

Familiarity with fundamental Azure Databricks concepts.

Have questions about this course?

We can help with curriculum details, delivery options, pricing, or anything else. Reach out and we’ll point you in the right direction.

Contact us
}