Text-to-SQL Spring AI Implementation with RAG

Name: Text-to-SQL Spring AI Implementation with RAG
Rating: 3.9 (6 reviews)

Build a Text-to-SQL application using Spring AI 1.1

Created byFu Cheng

Last updated 11/2025

English

What you'll learn

Learn how to use Spring AI 1.0 to build AI applications
Text-to-SQL implementation using LLM and RAG
Database metadata searching using vector store
Function calling in Spring AI to execute SQL statements

Course content

10 sections • 41 lectures • 2h 57m total length

Course introduction2:11
Introduction of this Spring AI course.

Basic Text to SQL6:23
Basic text to SQL implementation using handwritten database metadata.
[Code & Demo] Basic text to SQL3:37
Code and demo of basic text to SQL implementation
Database metadata extraction9:08
Extract database metadata using JDBC API. Metadata is serialized into JSON string, then included in the prompt sent to LLM. Use a Spring AI advisor to update the system text of prompts.
[Code & Demo] Database metadata5:50
Low cardinality values5:55
Some columns in a database table only have a few unique values. Exact values of these columns must be used in SQL statements. These low cardinality values are included in the metadata.

Embedding model and vector store8:29
Introduction to embedding models and vector stores.

Use Chroma as the vector store.
[Code & Demo] Chroma2:16
Database metadata index4:06
Use an offline process to extract database metadata, convert into Spring AI documents, and save to a vector store.
[Code & Demo] Database metadata index4:18
Generate table summary using LLM2:34
Use LLM to generate summary of database tables.
[Code & Demo] Generate table summary2:40
Include SQL sample queries3:55
Collect history SQL statements and include them in the prompt sent to LLM.
[Code & Demo] Include SQL sample queries2:58
Generate SQL statement summary using LLM3:19
Generate summary of SQL statements using LLM.
Reduce LLM prompt content size4:24
Different approaches to reduce the size of prompt content sent to LLM.
Table metadata stored in Postgres3:34
Table metadata stored in Postgres
Target driven generation2:41
Specify the JSON schema of query result, use LLM to generate SQL statement matching the schema

Prepare for deployment4:09
Prepare the application for deploying as a serverless function
Use Spring Cloud Function2:50
Use Spring Cloud Function to deploy the metadata indexer and Text-to-SQL application as serverless functions.
[Code & Demo] Function handlers for Spring Cloud Function3:13
Code of functions for metadata indexer and Text-to-SQL application.
Use AWS CDK to deploy serverless functions to AWS Lambda4:25
Use AWS CDK to deploy serverless functions to AWS Lambda.
[Code & Demo] Use AWS CDK to deploy functions9:14
Demo to use AWS CDK to deploy serverless functions.

Requirements

Basic knowledge of Java
Basic knowledge of Spring & Spring Boot
Basic knowledge of LLM

Description

Building AI applications is very popular these days. For Java developers, the best choice for building AI applications is using Spring AI. To learn how to use Spring AI to build AI applications, we need to have a concrete example. Text to SQL, is a typical usage of using AI to improve productivity. By using text to SQL, non-technical people use natural language to describe database query requirements. These queries are sent to LLM. LLM can generate SQL statements to answer user queries. LLM can also use tools to execute SQL statements, and return the query results to the user. Text to SQL is a good example of AI applications.

In this course, we will use Spring AI to create a text to SQL application. After learning this course, you will know:

How to use ChatClient to send requests to LLM and receive responses.
How to extract database metadata and include them in the prompt sent to LLM.
How to use Spring AI advisors to intercept ChatClient requests to process requests and responses.
How to use embedding model and vector store to implement semantic search of database metadata.
How to use LLM to generate summary of database tables and SQL statements.
How to use LLM to re-select tables automatically.
How to allow user to manually re-select tables using message history.
How to execute and validate SQL statements using functions.
How to deployment metadata indexer and Text-to-SQL application as serverless functions on AWS Lambda.
How to store table metadata in a database.
How to create a Text-to-SQL MCP server using Spring AI and MCP Java SDK.

This course covers all major aspects of Spring AI, including ChatClient, advisors, embedding models, vector stores, chat memory and function calling.

What you have learned in this course can help you build other AI applications using Spring AI.

The code has been updated to Spring AI 1.1 release version.

You can also get a free copy of the PDF book.

Source code: This course provides full source code of the text to SQL application. The source code can be downloaded from resource of 5th lecture. You can also send me your GitHub account email to access the private GitHub repository.

Who this course is for:

Java developer curious about building AI applications using Spring AI

Text-to-SQL Spring AI Implementation with RAG

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 2min

Spring AI Basic1 lecture • 6min

Basic Text to SQL5 lectures • 31min

Database metadata search using RAG12 lectures • 45min

Table re-selection5 lectures • 24min

Functions to execute and validate SQL statements4 lectures • 17min

Web UI1 lecture • 3min

Deployment5 lectures • 24min

MCP3 lectures • 17min

Updates4 lectures • 9min

Requirements

Description

Who this course is for: