rrezartprebreza/spring-boot-skills / skills/spring-boot-4/spring-ai-integration
spring-ai-integration
VerifiedUse when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI 2.0 ChatClient, prompt templates, embeddings, vector stores, and structured output. Use when user mentions Spring AI, LLM, ChatGPT, Claude, RAG, embeddings.
Spring AI Integration
Dependencies
<dependencyManagement>
<dependencies>
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-bom</artifactId>
<version>2.0.0</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
<dependencies>
<!-- Choose your model provider — pattern is spring-ai-starter-model-<provider> -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-model-anthropic</artifactId>
</dependency>
<!-- OR -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-model-openai</artifactId>
</dependency>
<!-- For RAG / vector search -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-vector-store-pgvector</artifactId>
</dependency>
<!-- QuestionAnswerAdvisor lives here — 2.0 renamed spring-ai-advisors-vector-store -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-vector-store-advisor</artifactId>
</dependency>
</dependencies>
Version pairing matters. Spring Boot 4 requires Spring AI 2.0 (
spring-ai-bom2.0.0); the 1.x line targets Boot 3 only. Starter coordinates followspring-ai-starter-model-<provider>(e.g.-model-anthropic,-model-openai) andspring-ai-starter-vector-store-<store>. Agents trained on pre-1.0 Spring AI emitspring-ai-<x>-spring-boot-starter— those names resolve to nothing in Maven Central. Also gone in 2.0:spring-ai-starter-model-azure-openai(use the OpenAI starter with an Azure base URL instead).
ChatClient — Basic Usage
@Service
@RequiredArgsConstructor
public class DocumentSummaryService {
private final ChatClient chatClient;
public String summarize(String conversationId, String content) {
return chatClient.prompt()
.advisors(a -> a.param(ChatMemory.CONVERSATION_ID, conversationId))
.user(u -> u.text("Summarize the following document in 3 bullet points:\n\n{content}")
.param("content", content))
.call()
.content();
}
// With system prompt
public String analyzeFinancial(String conversationId, String document, String language) {
return chatClient.prompt()
.advisors(a -> a.param(ChatMemory.CONVERSATION_ID, conversationId))
.system("You are a financial analyst. Respond in {language}.")
.system(s -> s.param("language", language))
.user(document)
.call()
.content();
}
}
Every call using the configured memory advisor must provide a user- or session-scoped
ChatMemory.CONVERSATION_ID. Never use one shared conversation ID for all users.
ChatClient Bean Configuration
@Configuration
public class AiConfig {
@Bean
public ChatMemory chatMemory() {
// InMemoryChatMemory is long gone. Use MessageWindowChatMemory —
// it caps history to a sliding window and defaults to an in-memory repository.
return MessageWindowChatMemory.builder()
.maxMessages(20)
.build();
}
@Bean
public ChatClient chatClient(ChatClient.Builder builder, ChatMemory chatMemory) {
return builder
.defaultSystem("You are a helpful assistant for an e-commerce platform.")
.defaultAdvisors(
MessageChatMemoryAdvisor.builder(chatMemory).build(), // builder, not new(...)
new SimpleLoggerAdvisor() // logs prompts/responses
)
.build();
}
}
// 2.0: the conversation id is REQUIRED on every call that goes through a memory advisor.
// ChatMemory.DEFAULT_CONVERSATION_ID is removed — omitting the param throws IllegalArgumentException.
public String chat(String sessionId, String message) {
return chatClient.prompt()
.user(message)
.advisors(a -> a.param(ChatMemory.CONVERSATION_ID, sessionId))
.call()
.content();
}
Prompt Templates (externalized)
// src/main/resources/prompts/analyze-order.st
// Analyze this order and identify any anomalies:
// Customer: {customerEmail}
// Items: {items}
// Total: {total}
// Flag any unusual patterns.
@Service
@RequiredArgsConstructor
public class OrderAnalysisService {
private final ChatClient chatClient;
@Value("classpath:prompts/analyze-order.st")
private Resource promptTemplate;
public String analyzeOrder(String conversationId, Order order) {
return chatClient.prompt()
.advisors(a -> a.param(ChatMemory.CONVERSATION_ID, conversationId))
.user(u -> u.text(promptTemplate)
.param("customerEmail", order.getCustomerEmail()) // must match {customerEmail} in the .st
.param("items", order.getItems().toString())
.param("total", order.getTotal()))
.call()
.content();
}
}
Structured Output
// Define the target record
public record OrderClassification(
String category,
String priority,
List<String> tags,
boolean requiresManualReview
) {}
@Service
public class OrderClassifier {
public OrderClassification classify(String orderDescription) {
return chatClient.prompt()
.user("Classify this order: " + orderDescription)
.call()
.entity(OrderClassification.class); // Spring AI handles JSON parsing
}
}
RAG Pipeline
@Configuration
public class RagConfig {
// No manual VectorStore bean — the spring-ai-starter-vector-store-pgvector
// starter auto-configures one. Just inject it. (The old `new PgVectorStore(...)`
// constructor is removed; if you must build one, use PgVectorStore.builder(...).)
@Bean
public ChatClient ragChatClient(ChatClient.Builder builder, VectorStore vectorStore) {
return builder
.defaultAdvisors(
QuestionAnswerAdvisor.builder(vectorStore)
.searchRequest(SearchRequest.builder().topK(5).build()) // builder, not defaults().withTopK()
.build()
)
.build();
}
}
@Service
@RequiredArgsConstructor
public class KnowledgeService {
private final VectorStore vectorStore;
private final ChatClient ragChatClient;
// Ingest documents
public void ingest(List<String> documents) {
List<Document> docs = documents.stream()
.map(content -> new Document(content))
.toList();
vectorStore.add(docs);
}
// Query with RAG
public String ask(String question) {
return ragChatClient.prompt()
.user(question)
.call()
.content();
}
}
Streaming Responses
@GetMapping(value = "/stream", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<String> stream(@RequestParam String prompt) {
return chatClient.prompt()
.user(prompt)
.stream()
.content();
}
application.yml
spring:
ai:
anthropic:
api-key: ${ANTHROPIC_API_KEY}
chat:
# 2.0 flattened the properties — the old chat.options.* nesting is dead
model: ${ANTHROPIC_MODEL}
max-tokens: 2048
temperature: 0.7 # 2.0 removed the 0.7 default — set it explicitly if you rely on it
# OR for OpenAI:
openai:
api-key: ${OPENAI_API_KEY}
chat:
model: ${OPENAI_MODEL}
vectorstore:
pgvector:
initialize-schema: true
dimensions: 1536
Gotchas
- Agent binds
.param("customer", ...)when the.stfile says{customerEmail}— the default renderer fails with "Not all variables were replaced"; keep param names and template placeholders identical - Agent uses Spring AI 1.x (
spring-ai-bom1.0.x) on Spring Boot 4 — 1.x targets Boot 3 only; Boot 4 requires Spring AI 2.0 - Agent uses pre-1.0 artifact names (
spring-ai-anthropic-spring-boot-starter) — the pattern isspring-ai-starter-model-anthropic - Agent configures
spring.ai.anthropic.chat.options.model— 2.0 flattened properties; drop the.optionssegment (spring.ai.anthropic.chat.model) - Agent passes built options to
.options(...)— 2.0 takes the builder:.options(AnthropicChatOptions.builder().maxTokens(2048)), no.build() - Agent writes
new MessageChatMemoryAdvisor(new InMemoryChatMemory())— both long removed; useMessageChatMemoryAdvisor.builder(chatMemory)+MessageWindowChatMemory - Agent omits the conversation id on a memory-advisor call — mandatory in 2.0 (
ChatMemory.DEFAULT_CONVERSATION_IDremoved); passa.param(ChatMemory.CONVERSATION_ID, ...)or getIllegalArgumentException - Agent uses
PromptChatMemoryAdvisor— removed in 2.0; useMessageChatMemoryAdvisor - Agent adds
spring-ai-advisors-vector-storeforQuestionAnswerAdvisor— renamed tospring-ai-vector-store-advisorin 2.0 - Agent writes
SearchRequest.defaults().withTopK(n)— useSearchRequest.builder().topK(n).build() - Agent hardcodes API keys — always use environment variables /
${...} - Agent hardcodes provider model IDs - configure them externally because model catalogs change
- Agent builds prompts with string concatenation — use
.param()template variables - Agent puts prompts inline in code — externalize to
src/main/resources/prompts/ - Agent ignores structured output — use
.entity(MyClass.class)instead of parsing manually - Agent uses
.entity(List.class)for a list — generics erase; passnew ParameterizedTypeReference<List<X>>() {} - Agent skips error handling for API calls — wrap in try/catch, handle
NonTransientAiException(don't retry) vsTransientAiException(retry) - Agent uses wrong model string — verify model names against provider docs
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |