Text to SQL: Amazon Redshift Serverless for Generative SQL in Amazon Q

Course details

Are you ready to extract data and gain faster insights? In this course, learn how to enable text to SQL with AI-powered assistant Amazon Q in Amazon Redshift Query Editor to generate queries with prompt engineering and retrieval-augemented generation (RAG). Instructor Wendy Wong takes you through the architecture of Amazon Q to help you identify table schemas from your data and redefine the heavy lifting of figuring out table relationships. Along the way, learn to use prompts in natural language to produce customized SQL. By the end of this course, you’ll be prepared to use Amazon Q to help you to troubleshoot coding errors and regenerate code that you can run in SQL Notebook.

Learning objectives
Discover and extract data by using natural language to generate SQL queries.
Create intermediate- and advanced-level SQL queries and rerun them directly from SQL Notebook.
Identify and debug SQL errors using the generative SQL console.
Explain the benefits of using Amazon Q generative SQL in Amazon Redshift Query Editor. Describe the solution architecture of how SQL queries are generated based on context with prompt engineering and retrieval augmented generation (RAG).

Skills covered

Amazon QDesktop DatabasesSQLDatabase AdministrationData EngineeringDatabase DevelopmentAmazon Web Services (AWS)AmazonGenerative AIDatabase ManagementData AnalysisArtificial Intelligence (AI)Programming LanguagesData ScienceBusiness Analysis and StrategyBusiness Software and ToolsOpen SourceSoftware DevelopmentDeep Dive (X:Y)

Concepts

0. Introduction

01 - Text to SQL with Amazon Q
02 - What you should know

1. Text to SQL

03 - Applications of generative AI
04 - Generating code with prompt engineering
05 - Common use cases

2. Generative SQL in Amazon Redshift Serverless

06 - Case study 1
07 - Case study 2
08 - Amazon Q generative SQL in Amazon Redshift
09 - Understanding the benefit of Redshift

3. Getting Started with Generative SQL

10 - Natural language processing (NLP)
11 - Use cases for NLP
12 - Prerequisite knowledge
13 - Supported AWS regions
14 - Understanding pricing options
15 - Data privacy and security
16 - Experimentation

4. Solution Architecture of LLMs

17 - Generating SQL queries
18 - Understanding the solution architecture
19 - Prompt engineering in SQL query context
20 - RAG in SQL query context
21 - How are SQL queries generated
22 - Accessing query history
23 - Best practice - Asking a good question
24 - Troubleshooting SQL query errors

5. Create a Serverless Database

25 - Introduction to Amazon Redshift
26 - Amazon Redshift provisioned clusters
27 - Understanding Amazon Redshift Serverless
28 - Spinning up a database in Amazon Redshift Serverless
29 - Understanding IAM permissions
30 - Creating a workgroup
31 - Launching query editor

6. Create a Table

32 - Introducing the datasets
33 - Open data source options
34 - Writing a query to create a table in Amazon Redshift Query Editor
35 - Loading data into the table
36 - Understanding structured data
37 - Defining a schema
38 - Viewing the schema
39 - Tables and schemas

7. Intermediate SQL

40 - Producing more relevant SQL queries
41 - Debugging SQL error messages
42 - Filtering data
43 - Multi-table joins
44 - Creating CASE statements
45 - Exploring nested queries
46 - Determining the number of working days between two dates
47 - Creating a view

8. Advanced SQL

48 - Computing a running total
49 - Finding duplicate rows
50 - Counting duplicate rows
51 - Obtaining all rows where the result is in a subquery result
52 - Grouping data with ROLLUP
53 - Finding the top 10 rows of a result set
54 - Ranking the rows on specific criteria
55 - Listing the highest row of a result set

Conclusion

56 - Cleaning up resources
57 - Summarizing the course
58 - Resources for additional learning