1-Day Instructor-Led Training
Microsoft Official Content
Hands On Labs
After-Course Instructor-Coaching Included
#8761
Implement Generative AI engineering with Azure Databricks (DP-3028)
Course 8761
- Duration: 1 day
- Language: English
- Level: Intermediate
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.
Azure Databricks Generative AI Course Delivery Methods
In-Person
Online
Upskill your whole team by bringing Private Team Training to your facility.
Azure Databricks Generative AI Course Information
In this course, you will:
- Gain hands-on experience implementing Retrieval-Augmented Generation (RAG) and fine-tuning large language models (LLMs).
- Explore multi-stage reasoning techniques using LangChain, LlamaIndex, Haystack, and DSPy.
- Understand and apply LLMOps practices for model deployment, monitoring, and governance with MLflow and Unity Catalog.
- Incorporate responsible AI principles, including risk mitigation and ethical considerations.
- Build and operationalize generative AI solutions using Azure Databricks and Apache Spark.
- Acquire in-demand generative AI skills in a focused, one-day training format.
Prerequisites
Before starting this module, you should be familiar with fundamental Azure Databricks concepts.
Azure Databricks Generative AI Course Outline
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
Implement Retrieval Augmented Generation (RAG) with Azure Databricks
- 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
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
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
Evaluate language models with Azure Databricks
- Explore LLM evaluation
- Evaluate LLMs and AI systems
- Evaluate LLMs with standard metrics
- Describe LLM-as-a-judge for evaluation
- Exercise – Evaluate an Azure OpenAI model
Review responsible AI principles for language models in Azure Databricks
- What is responsible AI?
- Identify risks
- Mitigate issues
- Use key security tooling to protect your AI systems
- Exercise – Implement responsible AI
Implement LLMOps in Azure Databricks
- Transition from traditional MLOps to LLMOps
- Understand model deployments
- Describe MLflow deployment capabilities
- Use Unity Catalog to manage models
- Exercise – Implement LLMOps
Speak with a Learning Consultant
Speak with a Learning Consultant
Fill out the form below or call 888-843-8733
Need Help Finding The Right Training Solution?
Our training advisors are here for you.
Azure Databricks Generative AI Course FAQs
This course is ideal for AI Engineers, Data Scientists, and Machine Learning Engineers who want to design, build, and operationalize large language model (LLM) solutions using Azure Databricks.
Yes. Participants should have prior experience with Python, familiarity with machine learning concepts, and basic knowledge of Azure Databricks and Apache Spark.
Yes. The course includes practical labs where you’ll work directly in Azure Databricks to apply concepts like RAG, fine-tuning, and LLMOps to real-world scenarios.
This is a one-day, instructor-led training that blends lectures, demonstrations, and hands-on labs for an immersive learning experience.