Anthropic Chat

ChatClient chatClient = ChatClient.create(chatModel);

// For Claude 3.7 Sonnet - explicit thinking configuration required
ChatResponse response = chatClient.prompt()
    .options(AnthropicChatOptions.builder()
        .model("claude-3-7-sonnet-latest")
        .temperature(1.0)  // Temperature should be set to 1 when thinking is enabled
        .maxTokens(8192)
        .thinking(AnthropicApi.ThinkingType.ENABLED, 2048)  // Must be ≥1024 && < max_tokens
        .build())
    .user("Are there an infinite number of prime numbers such that n mod 4 == 3?")
    .call()
    .chatResponse();

// For Claude 4 models - thinking is enabled by default
ChatResponse response4 = chatClient.prompt()
    .options(AnthropicChatOptions.builder()
        .model("claude-opus-4-0")
        .maxTokens(8192)
        // No explicit thinking configuration needed
        .build())
    .user("Are there an infinite number of prime numbers such that n mod 4 == 3?")
    .call()
    .chatResponse();

// Process the response which may contain thinking content
for (Generation generation : response.getResults()) {
    AssistantMessage message = generation.getOutput();
    if (message.getText() != null) {
        // Regular text response
        System.out.println("Text response: " + message.getText());
    }
    else if (message.getMetadata().containsKey("signature")) {
        // Thinking content
        System.out.println("Thinking: " + message.getMetadata().get("thinking"));
        System.out.println("Signature: " + message.getMetadata().get("signature"));
    }
}

ChatClient chatClient = ChatClient.create(chatModel);

// For Claude 3.7 Sonnet - explicit thinking configuration
Flux<ChatResponse> responseFlux = chatClient.prompt()
    .options(AnthropicChatOptions.builder()
        .model("claude-3-7-sonnet-latest")
        .temperature(1.0)
        .maxTokens(8192)
        .thinking(AnthropicApi.ThinkingType.ENABLED, 2048)
        .build())
    .user("Are there an infinite number of prime numbers such that n mod 4 == 3?")
    .stream();

// For Claude 4 models - thinking is enabled by default
Flux<ChatResponse> responseFlux4 = chatClient.prompt()
    .options(AnthropicChatOptions.builder()
        .model("claude-opus-4-0")
        .maxTokens(8192)
        // No explicit thinking configuration needed
        .build())
    .user("Are there an infinite number of prime numbers such that n mod 4 == 3?")
    .stream();

// For streaming, you might want to collect just the text responses
String textContent = responseFlux.collectList()
    .block()
    .stream()
    .map(ChatResponse::getResults)
    .flatMap(List::stream)
    .map(Generation::getOutput)
    .map(AssistantMessage::getText)
    .filter(text -> text != null && !text.isBlank())
    .collect(Collectors.joining());

var imageData = new ClassPathResource("/multimodal.test.png");

var userMessage = new UserMessage("Explain what do you see on this picture?",
        List.of(new Media(MimeTypeUtils.IMAGE_PNG, this.imageData)));

ChatResponse response = chatModel.call(new Prompt(List.of(this.userMessage)));

logger.info(response.getResult().getOutput().getContent());

The image shows a close-up view of a wire fruit basket containing several pieces of fruit.
...

var pdfData = new ClassPathResource("/spring-ai-reference-overview.pdf");

var userMessage = new UserMessage(
        "You are a very professional document summarization specialist. Please summarize the given document.",
        List.of(new Media(new MimeType("application", "pdf"), pdfData)));

var response = this.chatModel.call(new Prompt(List.of(userMessage)));