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

Objectives

Implement Generative AI Engineering with Azure Databricks Course Objectives:
• Describe the fundamentals of Generative AI and Large Language Models (LLMs).
• Implement Retrieval Augmented Generation (RAG) workflows using Azure Databricks.
• Build and deploy multi-stage reasoning systems with popular open-source libraries.
• Fine-tune Azure OpenAI models using customized datasets.
• Evaluate LLMs using key metrics and LLM-as-a-judge frameworks.
• Apply responsible AI principles and implement LLMOps with MLflow and Unity Catalog.

Target Audience
• Data Scientist

Course Outline

1) Get started with language models in Azure Databricks
• Describe Generative AI
• Describe Large Language Models (LLMs)
• Identify key components of LLM applications
• Use LLMs for Natural Language Processing (NLP) tasks
• Lab: Explore language models

2) Implement Retrieval Augmented Generation RAG with Azure Databricks
• Set up a RAG workflow
• Prepare your data for RAG
• Retrieve relevant documents with vector search
• Improve model accuracy by reranking your search results
• Lab: Set up RAG

3) Implement multistage reasoning in Azure Databricks
• Identify the need for multi-stage reasoning systems
• Describe a multi-stage reasoning workflow
• Implement multi-stage reasoning with libraries like LangChain, LlamaIndex, Haystack, and the DSPy framework
• Lab: Implement multi-stage reasoning with LangChain

4) Finetune language models with Azure Databricks
• Understand when to use fine-tuning
• Prepare your data for fine-tuning
• Fine-tune an Azure OpenAI model
• Lab: Fine-tune an Azure OpenAI model

5) Evaluate language models with Azure Databricks
• Compare LLM and traditional ML evaluations
• Describe the relationship between LLM evaluation and evaluation of entire AI systems
• Describe generic LLM evaluation metrics like accuracy, perplexity, and toxicity
• Describe LLM-as-a-judge for evaluation
• Lab: Evaluate an Azure OpenAI model

6) Review responsible AI principles for language models in Azure Databricks
• Describe the responsible AI principles for implementation of language models
• Identify the ethical considerations for language models
• Mitigate the risks associated with language models
• Implement key security tooling for language models
• Lab: Implement responsible AI

7) Implement LLMOps in Azure Databricks
• Describe the LLM lifecycle overview
• Identify the model deployment option that best fits your needs
• Use MLflow and Unity Catalog to implement LLMops
• Lab: Implement LLMOps