Building Reliable Conversational Agents with Genie - Mandarin Chinese

本课程将教您如何设计、构建和维护 Databricks Genie Agent——一种自然语言界面，使业务用户能够针对受治理的数据提出问题，并获得基于 SQL 的答案，而无需编写代码。

您将了解 Genie Agent 如何融入 Databricks AI/BI 产品系列，以及它们如何将自然语言转换为可靠的 SQL 查询。本课程重点介绍如何创建一个能够提供准确、一致且可信结果的 Genie Agent。

您将遵循完整的端到端工作流，从理解源数据、定义基准，到使用全套 Knowledge Store 管理工具对 Genie Agent 进行配置和优化。这些工具包括元数据、同义词、提示匹配、SQL 逻辑、示例查询和文本说明。

您还将学习如何通过 Genie One 与业务用户共享 Genie Agent，了解 Unity Catalog 治理如何自动执行，并利用监控和用户反馈持续提升质量。

完成本课程后，您将能够创建和管理一个生产就绪的 Genie Agent，以可扩展的方式提供受治理的自助式对话分析。

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“下一课”按钮，否则可能导致 SCORM 模块无法标记为已完成。

Skill Level

Associate

Duration

Prerequisites

本课程的内容面向具备以下技能、知识和能力的参与者开发：

• 熟悉 Databricks workspace 的基本操作——您能够在 workspace UI 中进行导航、附加 compute 资源并运行 Notebooks。

• 熟悉 Unity Catalog 的相关概念——您了解 Unity Catalog 中的目录、架构和表。具备权限、标签或列掩码的使用经验有所帮助，但并非必需。

• 具备中级 SQL 能力——您能够读写 SQL 查询，包括 SELECT、JOIN、GROUP BY 及聚合函数。

• 能够访问具有 Databricks SQL 权限的 Databricks workspace，并对 serverless SQL warehouse 拥有 CAN USE 权限。

Self-Paced

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

Customer registration Partner registration

See all our registration options

Registration options

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

Self-Paced

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

Instructor-Led

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

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

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

Building Enterprise Applications with Databricks Apps - Mandarin Chinese

本课程介绍 Databricks Apps——一项赋能开发者直接在 Databricks 平台上构建和部署安全数据与 AI 应用的新功能。本课程主要面向数据科学家、数据工程师以及需要创建自定义应用的开发者，帮助他们将数据洞察以易于访问的方式呈现给组织内的非技术用户。

课程首先概述 Databricks Apps 的主要组成部分，随后演示如何部署一个与外部服务集成的简单应用。接下来，您将学习如何构建和部署与 Databricks 平台功能集成的智能数据驱动应用。课程还将介绍如何在 Databricks 环境之外开发应用，最后以详细讲解实施安全可靠的企业级应用的最佳实践作为结尾。

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“下一课”按钮，否则可能导致 SCORM 模块无法标记为已完成。

Paid & Subscription

Lab

Associate

Building ETL Pipelines with SQL

This course teaches how to build production-ready ETL pipelines using pure SQL on the Databricks Data Intelligence Platform. Students learn Streaming Tables with Auto Loader for incremental ingestion, Materialized Views with incremental refresh for Silver-to-Gold transformations, AUTO CDC (FLOW AUTO CDC) for declarative SCD Type 1 and Type 2 dimension management, and Apache Spark Declarative Pipelines (SDP) to group these objects into production multi-table pipelines with data quality expectations, PRIVATE tables, and unified monitoring. The course follows a realistic retail dataset through the medallion architecture (Bronze → Silver → Gold). Orchestrating with Lakeflow Jobs is available as a bonus module.

Note: For SCORM lecture files, please ensure that you close the SCORM window after completing the content. Do not click the ‘Next Lesson’ button, as doing so may prevent the SCORM module from being marked as complete.

Paid & Subscription

Lab

Associate

Building Databricks Apps with Genie Code and Lakebase

Databricks Apps make it possible to build and deploy interactive data and AI applications directly on the Databricks platform. But successful AI-assisted development is about more than generating code—it's about developing an effective workflow.

In this course, you'll learn to build a Lakebase-backed Databricks App from the ground up using Genie Code as your AI development assistant. Along the way, you'll learn a practical, repeatable approach to AI-assisted development: clearly specifying intent before generating code, working in small, verifiable increments, leveraging reusable Genie Code Skills, and treating AI-generated output as something to review and refine—not simply accept.

You'll create and deploy a Databricks App, provision and connect a Lakebase database as its transactional store, implement CRUD operations, and use Genie Code to accelerate common development tasks. By the end of the course, you'll not only have a working application, but also a practical framework for collaborating effectively with AI on future software projects.

Paid & Subscription

Lab

Associate