Generative AI Application Deployment and Monitoring
(1/2 day)
Course Description
Ready to learn how to deploy, operationalize, and monitor generative AI applications? This content will help you gain skills in the deployment of generative AI applications using tools like Model Serving. We’ll also cover how to operationalize generative AI applications following best practices and recommended architectures. Finally, we’ll discuss the idea of monitoring generative AI applications and their components using Lakehouse Monitoring.
Objectives
- Explain best practices for deploying generative AI applications using tools like Model Serving.
- Explain how to operationalize generative AI applications following best practices and recommended architectures.
- Use Lakehouse Monitoring to monitor generative AI applications and their components.
Prerequisites
- Familiarity with natural language processing concepts
- Familiarity with prompt engineering/prompt engineering best practices
- Familiarity with the Databricks Data Intelligence Platform
- Familiarity with RAG (preparing data, building a RAG architecture, concepts like embedding, vectors, vector databases, etc.)
- Experience with building LLM applications using multi-stage reasoning LLM chains and agents
- Familarity with Databricks Data Intelligence Platform tools for evaluation and governance.
Course Outline
Module 1: Model Deployment Fundamentals
- Model Management
- Deployment Methods
Module 2: Batch Deployment
- Introduction to Batch Deployment
- Batch Inference
- Batch Inference Workflows using SLM
Module 3: Real-Time Deployment
- Introduction to Real-Time Deployment
- Databricks Model Serving
- Serving External Models with Model Serving
- Deploying an LLM Chain to Databricks Model Serving
- Custom Model Deployment and A/B Testing
Module 4: AI System Monitoring
- AI Application Monitoring
- Online Monitoring an LLM RAG Chain
Module 5: LLMOps Concepts
- MLOps Primer
- LLMOps vs MLOps
