Generative AI Solution Development
(1/2 day)
Course Description
This is your introduction to contextual generative AI solutions using the retrieval-augmented generation (RAG) method. First, you’ll be introduced to RAG architecture and the significance of contextual information using Mosaic AI Playground. Next, we’ll show you how to prepare data for generative AI solutions and connect this process with building a RAG architecture. Finally, you’ll explore concepts related to context embedding, vectors, vector databases, and the utilization of Mosaic AI Vector Search.
Objectives
- Describe RAG architecture.
- Use Mosaic AI Playground to explore the significance of contextual information.
- Prepare data for generative AI solutions.
- Connect data preparation for generative AI solutions to building a RAG architecture.
- Describe fundamental concepts about context embedding, vectors, vector databases, and the utlization of Mosaic AI Vector Search.
Prerequisites
- Familiarity with natural language processing concepts
- Familiarity with prompt engineering/prompt engineering best practices
- Familiarity with the Databricks Data Intelligence Platform
Course Outline
Module 1: Introduction to RAG
- What is RAG?
- In Context Learning with AI Playground
Module 2: Preparing Data for RAG Solutions
- Data Storage and Governance
- Data Extraction and Chunking
- Embedding Model
- Data Preparation in Databricks
Module 3: Vector Search
- Introduction to Vector Stores
- Vector Search Process and Performance
- Choosing the right Vector Database
- Mosaic AI Vector Search
- Creating a Vector Search Index
Module 4: Assembling and Evaluating a RAG Application
- MLflow
- Evaluating a RAG Application and Continual Learning
- Assembling a RAG Application
