Skip to main content

Get Started with Databricks for Generative AI

This course offers a practical introduction to the Databricks Data Intelligence Platform, focusing on its key components and features for building and deploying generative AI systems. Participants will learn how Databricks facilitates the development of scalable generative AI solutions and explore tools such as AI Search, the Agent Framework, and MLflow's generative AI capabilities for model tracking and logging. This course includes hands-on experience in constructing and evaluating Retrieval-Augmented Generation (RAG) pipelines, deploying generative AI agents, and leveraging evaluation frameworks to optimize performance. By the end of the course, learners will be equipped with the skills to design, deploy, and monitor common generative AI applications on the Databricks Data Intelligence Platform.


Languages Available: English | 日本語 | Português BR | 한국어 | Français

Skill Level
Onboarding
Duration
2h
Prerequisites

The content was developed for participants with these skills/knowledge/abilities:

• Familiarity with the Databricks Data Intelligence Platform and basic workspace operations (create clusters, run code in notebooks, use basic notebook operations)

• Basic knowledge of Python programming and working with APIs (Databricks SDK, external model integrations)

• Understanding of machine learning fundamentals, including model training, evaluation, and deployment concepts

• Basic familiarity with generative AI concepts (large language models, prompt engineering, hallucinations, retrieval-augmented generation)

• Intermediate experience with Unity Catalog for data governance and model registry operations

• Basic knowledge of vector search and similarity search concepts for document retrieval

• Familiarity with MLflow for experiment tracking, model logging, and evaluation frameworks

• Understanding of Delta Lake and data management concepts (tables, schemas, data formats)

Outline

• Databricks AI Overview

• Prompt Engineering with AI Playground

• Build & Register a Retrieval Pipeline

• Evaluating and Deploying AI Systems

• Introduction to Agent Bricks

• LAB - End-to-end Retrieval Pipeline on Databricks

Upcoming Public Classes

Date
Time
Your Local Time
Language
Price
Oct 20
12 PM - 02 PM (Asia/Singapore)
-
English
Free
Nov 12
09 AM - 11 AM (America/Los_Angeles)
-
English
Free
Dec 03
09 AM - 11 AM (America/Los_Angeles)
-
English
Free
Jan 07
09 AM - 11 AM (America/Los_Angeles)
-
English
Free

Public Class Registration

If your company has purchased success credits or has a learning subscription, please fill out the Training Request form. Otherwise, you can register below.

Private Class Request

If your company is interested in private training, please submit a request.

See all our registration options

Registration options

Databricks has a delivery method for wherever you are on your learning journey

Runtime

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Register now

Instructors

Instructor-Led

Public and private courses taught by expert instructors across half-day to two-day courses

Register now

Learning

Blended Learning

Self-paced and weekly instructor-led sessions for every style of learner to optimize course completion and knowledge retention. Go to Subscriptions Catalog tab to purchase

Purchase now

Scale

Skills@Scale

Comprehensive training offering for large scale customers that includes learning elements for every style of learning. Inquire with your account executive for details

Upcoming Public Classes

Data Engineer

Build Data Pipelines with Apache Spark Declarative Pipelines - Mandarin Chinese

本课程向用户介绍使用 Databricks 中的 Apache Spark™ Declarative Pipelines (SDP) 构建数据管道所需的基本概念和技能,涵盖通过多个流式处理表和物化视图进行增量批处理或流式处理摄取与处理。本课程专为初次接触 Spark Declarative Pipelines 的数据工程师设计,全面介绍核心组件,包括增量数据处理、流式处理表、物化视图和临时视图,并重点说明其各自的用途与区别。

课程涵盖以下主题:

• 使用 Spark Declarative Pipelines 中的多文件编辑器,通过 SQL 开发和调试 ETL 管道(并提供 Python 代码示例)

• Spark Declarative Pipelines 如何通过管道图形跟踪管道中的数据依赖关系

• 配置管道 compute 资源、数据资产、触发器模式及其他高级选项

随后,课程介绍 Spark Declarative Pipelines 中的数据质量期望,引导用户将期望集成到管道中,以验证和强制执行数据完整性。学员还将浏览如何将管道投入生产,包括调度选项,以及启用管道事件日志记录以监控管道性能和健康状况。

最后,课程介绍如何在 Spark Declarative Pipelines 中使用 AUTO CDC INTO 语法实现变更数据捕获 (CDC),以管理缓慢变化维度(SCD Type 1 和 Type 2),帮助用户将 CDC 集成到自己的管道中。

注意:对于 SCORM 课程文件,请确保完成内容后关闭 SCORM 窗口。请勿点击‘Next Lesson’按钮,否则可能会导致 SCORM 模块无法标记为已完成。

Free
2h
Associate

Questions?

If you have any questions, please refer to our Frequently Asked Questions page.