spring-ai-integration

Name: spring-ai-integration
Author: rrezartprebreza

174stars33forks

How to install spring-ai-integration?

rrezartprebreza/spring-boot-skills/spring-ai-integration

$npx -y skills add rrezartprebreza/spring-boot-skills --skill spring-ai-integration

Installs into the current project.

Summary

Use when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.

Files · 1

View on GitHub

SKILL.md

1	# Spring AI Integration
2
3	## Dependencies
4
5	```xml
6	<dependencyManagement>
7	<dependencies>
8	<dependency>
9	<groupId>org.springframework.ai</groupId>
10	<artifactId>spring-ai-bom</artifactId>
11	<version>1.0.0</version>
12	<type>pom</type>
13	<scope>import</scope>
14	</dependency>
15	</dependencies>
16	</dependencyManagement>
17
18	<dependencies>
19	<!-- Choose your model provider — 1.0 GA renamed every starter to spring-ai-starter-* -->
20	<dependency>
21	<groupId>org.springframework.ai</groupId>
22	<artifactId>spring-ai-starter-model-anthropic</artifactId>
23	</dependency>
24	<!-- OR -->
25	<dependency>
26	<groupId>org.springframework.ai</groupId>
27	<artifactId>spring-ai-starter-model-openai</artifactId>
28	</dependency>
29
30	<!-- For RAG / vector search -->
31	<dependency>
32	<groupId>org.springframework.ai</groupId>
33	<artifactId>spring-ai-starter-vector-store-pgvector</artifactId>
34	</dependency>
35	</dependencies>
36	```
37
38	> Watch the artifact names. 1.0 GA dropped the old `spring-ai-<x>-spring-boot-starter`
39	> coordinates. The pattern is now `spring-ai-starter-model-<provider>` (e.g. `-model-anthropic`,
40	> `-model-openai`) and `spring-ai-starter-vector-store-<store>`. Agents trained on pre-GA Spring AI
41	> will emit the dead names — they resolve to nothing in Maven Central.
42
43	## ChatClient — Basic Usage
44
45	```java
46	@Service
47	@RequiredArgsConstructor
48	public class DocumentSummaryService {
49
50	private final ChatClient chatClient;
51
52	public String summarize(String content) {
53	return chatClient.prompt()
54	.user(u -> u.text("Summarize the following document in 3 bullet points:\n\n{content}")
55	.param("content", content))
56	.call()
57	.content();
58	}
59
60	// With system prompt
61	public String analyzeFinancial(String document, String language) {
62	return chatClient.prompt()
63	.system("You are a financial analyst. Respond in {language}.")
64	.system(s -> s.param("language", language))
65	.user(document)
66	.call()
67	.content();
68	}
69	}
70	```
71
72	## ChatClient Bean Configuration
73
74	```java
75	@Configuration
76	public class AiConfig {
77
78	@Bean
79	public ChatMemory chatMemory() {
80	// 1.0 GA: InMemoryChatMemory is GONE. Use MessageWindowChatMemory —
81	// it caps history to a sliding window and defaults to an in-memory repository.
82	return MessageWindowChatMemory.builder()
83	.maxMessages(20)
84	.build();
85	}
86
87	@Bean
88	public ChatClient chatClient(ChatClient.Builder builder, ChatMemory chatMemory) {
89	return builder
90	.defaultSystem("You are a helpful assistant for an e-commerce platform.")
91	.defaultAdvisors(
92	MessageChatMemoryAdvisor.builder(chatMemory).build(), // GA: builder, not new(...)
93	new SimpleLoggerAdvisor() // logs prompts/responses
94	)
95	.build();
96	}
97	}
98	```
99
100	## Prompt Templates (externalized)
101
102	```java
103	// src/main/resources/prompts/analyze-order.st
104	// Analyze this order and identify any anomalies:
105	// Customer: {customer}
106	// Items: {items}
107	// Total: {total}
108	// Flag any unusual patterns.
109
110	@Service
111	public class OrderAnalysisService {
112
113	@Value("classpath:prompts/analyze-order.st")
114	private Resource promptTemplate;
115
116	public String analyzeOrder(Order order) {
117	return chatClient.prompt()
118	.user(u -> u.text(promptTemplate)
119	.param("customer", order.getCustomerEmail())
120	.param("items", order.getItems().toString())
121	.param("total", order.getTotal()))
122	.call()
123	.content();
124	}
125	}
126	```
127
128	## Structured Output
129
130	```java
131	// Define the target record
132	public record OrderClassification(
133	String category,
134	String priority,
135	List<String> tags,
136	boolean requiresManualReview
137	) {}
138
139	@Service
140	public class OrderClassifier {
141
142	public OrderClassification classify(String orderDescription) {
143	return chatClient.prompt()
144	.user("Classify this order: " + orderDescription)
145	.call()
146	.entity(OrderClassification.class); // Spring AI handles JSON parsing
147	}
148	}
149	```
150
151	## RAG Pipeline
152
153	```java
154	@Configuration
155	public class RagConfig {
156
157	// No manual VectorStore bean — the spring-ai-starter-vector-store-pgvector
158	// starter auto-configures one. Just inject it. (The old `new PgVectorStore(...)`
159	// constructor is removed in GA; if you must build one, use PgVectorStore.builder(...).)
160
161	@Bean
162	public ChatClient ragChatClient(ChatClient.Builder builder, VectorStore vectorSt

People who liked this also viewed

6 picks

Type

spring-ai-integration

174stars33forks

View on GitHub

How to install spring-ai-integration?

rrezartprebreza/spring-boot-skills/spring-ai-integration

$npx -y skills add rrezartprebreza/spring-boot-skills --skill spring-ai-integration

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Spring AI Integration
2
3	## Dependencies
4
5	```xml
6	<dependencyManagement>
7	<dependencies>
8	<dependency>
9	<groupId>org.springframework.ai</groupId>
10	<artifactId>spring-ai-bom</artifactId>
11	<version>1.0.0</version>
12	<type>pom</type>
13	<scope>import</scope>
14	</dependency>
15	</dependencies>
16	</dependencyManagement>
17
18	<dependencies>
19	<!-- Choose your model provider — 1.0 GA renamed every starter to spring-ai-starter-* -->
20	<dependency>
21	<groupId>org.springframework.ai</groupId>
22	<artifactId>spring-ai-starter-model-anthropic</artifactId>
23	</dependency>
24	<!-- OR -->
25	<dependency>
26	<groupId>org.springframework.ai</groupId>
27	<artifactId>spring-ai-starter-model-openai</artifactId>
28	</dependency>
29
30	<!-- For RAG / vector search -->
31	<dependency>
32	<groupId>org.springframework.ai</groupId>
33	<artifactId>spring-ai-starter-vector-store-pgvector</artifactId>
34	</dependency>
35	</dependencies>
36	```
37
38	> Watch the artifact names. 1.0 GA dropped the old `spring-ai-<x>-spring-boot-starter`
39	> coordinates. The pattern is now `spring-ai-starter-model-<provider>` (e.g. `-model-anthropic`,
40	> `-model-openai`) and `spring-ai-starter-vector-store-<store>`. Agents trained on pre-GA Spring AI
41	> will emit the dead names — they resolve to nothing in Maven Central.
42
43	## ChatClient — Basic Usage
44
45	```java
46	@Service
47	@RequiredArgsConstructor
48	public class DocumentSummaryService {
49
50	private final ChatClient chatClient;
51
52	public String summarize(String content) {
53	return chatClient.prompt()
54	.user(u -> u.text("Summarize the following document in 3 bullet points:\n\n{content}")
55	.param("content", content))
56	.call()
57	.content();
58	}
59
60	// With system prompt
61	public String analyzeFinancial(String document, String language) {
62	return chatClient.prompt()
63	.system("You are a financial analyst. Respond in {language}.")
64	.system(s -> s.param("language", language))
65	.user(document)
66	.call()
67	.content();
68	}
69	}
70	```
71
72	## ChatClient Bean Configuration
73
74	```java
75	@Configuration
76	public class AiConfig {
77
78	@Bean
79	public ChatMemory chatMemory() {
80	// 1.0 GA: InMemoryChatMemory is GONE. Use MessageWindowChatMemory —
81	// it caps history to a sliding window and defaults to an in-memory repository.
82	return MessageWindowChatMemory.builder()
83	.maxMessages(20)
84	.build();
85	}
86
87	@Bean
88	public ChatClient chatClient(ChatClient.Builder builder, ChatMemory chatMemory) {
89	return builder
90	.defaultSystem("You are a helpful assistant for an e-commerce platform.")
91	.defaultAdvisors(
92	MessageChatMemoryAdvisor.builder(chatMemory).build(), // GA: builder, not new(...)
93	new SimpleLoggerAdvisor() // logs prompts/responses
94	)
95	.build();
96	}
97	}
98	```
99
100	## Prompt Templates (externalized)
101
102	```java
103	// src/main/resources/prompts/analyze-order.st
104	// Analyze this order and identify any anomalies:
105	// Customer: {customer}
106	// Items: {items}
107	// Total: {total}
108	// Flag any unusual patterns.
109
110	@Service
111	public class OrderAnalysisService {
112
113	@Value("classpath:prompts/analyze-order.st")
114	private Resource promptTemplate;
115
116	public String analyzeOrder(Order order) {
117	return chatClient.prompt()
118	.user(u -> u.text(promptTemplate)
119	.param("customer", order.getCustomerEmail())
120	.param("items", order.getItems().toString())
121	.param("total", order.getTotal()))
122	.call()
123	.content();
124	}
125	}
126	```
127
128	## Structured Output
129
130	```java
131	// Define the target record
132	public record OrderClassification(
133	String category,
134	String priority,
135	List<String> tags,
136	boolean requiresManualReview
137	) {}
138
139	@Service
140	public class OrderClassifier {
141
142	public OrderClassification classify(String orderDescription) {
143	return chatClient.prompt()
144	.user("Classify this order: " + orderDescription)
145	.call()
146	.entity(OrderClassification.class); // Spring AI handles JSON parsing
147	}
148	}
149	```
150
151	## RAG Pipeline
152
153	```java
154	@Configuration
155	public class RagConfig {
156
157	// No manual VectorStore bean — the spring-ai-starter-vector-store-pgvector
158	// starter auto-configures one. Just inject it. (The old `new PgVectorStore(...)`
159	// constructor is removed in GA; if you must build one, use PgVectorStore.builder(...).)
160
161	@Bean
162	public ChatClient ragChatClient(ChatClient.Builder builder, VectorStore vectorSt

People who liked this also viewed

6 picks

Type