CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/maven-org-springframework-ai--spring-ai-client-chat

Spring AI Chat Client provides a fluent API for building AI-powered applications with LLMs, supporting advisors, streaming, structured outputs, and conversation memory

Overview
Eval results
Files

building-requests.mddocs/guides/

Building Requests

Learn how to configure requests using the fluent API.

Basic Request Structure

chatClient
    .prompt()                    // Start request
    .system("...")              // System message (optional)
    .user("...")                // User message
    .options(...)               // Model options (optional)
    .advisors(...)              // Advisors (optional)
    .call()                     // Execute
    .content();                 // Get response

User Messages

Simple Text

chatClient.prompt().user("What is Spring?").call().content();

With Parameters

chatClient
    .prompt()
    .user(spec -> spec
        .text("Explain {topic} in {language}")
        .param("topic", "dependency injection")
        .param("language", "Java")
    )
    .call()
    .content();

From Resource

import org.springframework.core.io.ClassPathResource;

chatClient
    .prompt()
    .user(new ClassPathResource("prompts/query.txt"))
    .call()
    .content();

With Media (Multimodal)

import org.springframework.ai.content.Media;
import org.springframework.util.MimeTypeUtils;

Media image = new Media(MimeTypeUtils.IMAGE_PNG, imageResource);

chatClient
    .prompt()
    .user(spec -> spec
        .text("Describe this image")
        .media(image)
    )
    .call()
    .content();

System Messages

Set context or behavior for the AI:

chatClient
    .prompt()
    .system("You are a Java expert. Provide concise answers.")
    .user("Explain interfaces")
    .call()
    .content();

With parameters:

chatClient
    .prompt()
    .system(spec -> spec
        .text("You are an expert in {domain}")
        .param("domain", "microservices")
    )
    .user("Explain service discovery")
    .call()
    .content();

Model Options

Configure temperature, max tokens, etc:

import org.springframework.ai.chat.options.ChatOptionsBuilder;

chatClient
    .prompt("Write a creative story")
    .options(ChatOptionsBuilder.builder()
        .withTemperature(0.9)       // Higher = more creative
        .withMaxTokens(1000)        // Limit response length
        .withTopP(0.95)             // Nucleus sampling
        .build())
    .call()
    .content();

Adding Advisors

Add interceptors for specific requests:

import org.springframework.ai.chat.client.advisor.SimpleLoggerAdvisor;

chatClient
    .prompt("Hello")
    .advisors(SimpleLoggerAdvisor.builder().build())
    .call()
    .content();

With parameters:

chatClient
    .prompt("Continue conversation")
    .advisors(spec -> spec
        .advisors(memoryAdvisor)
        .param("conversationId", "user-123")
    )
    .call()
    .content();

Tool Calling

Add functions the AI can call:

import org.springframework.ai.tool.ToolCallback;

ToolCallback weatherTool = ToolCallback.builder()
    .function("getWeather", this::getWeather)
    .description("Get current weather")
    .inputType(WeatherRequest.class)
    .build();

chatClient
    .prompt("What's the weather in Paris?")
    .toolCallbacks(weatherTool)
    .call()
    .content();

Complete Example

record Analysis(String summary, List<String> keyPoints, double confidence) {}

Analysis result = chatClient
    .prompt()
    .system(spec -> spec
        .text("You are an analyst. Focus on {aspect}.")
        .param("aspect", "technical details")
    )
    .user(spec -> spec
        .text("Analyze: {content}")
        .param("content", documentText)
    )
    .options(ChatOptionsBuilder.builder()
        .withTemperature(0.3)  // More deterministic
        .withMaxTokens(500)
        .build())
    .advisors(spec -> spec
        .advisors(validationAdvisor, loggerAdvisor)
        .param("requestId", UUID.randomUUID().toString())
    )
    .call()
    .entity(Analysis.class);

Best Practices

Parameter Validation

String topic = userInput;
if (topic == null || topic.isBlank()) {
    throw new IllegalArgumentException("Topic required");
}

chatClient.prompt().user(spec -> spec
    .text("Explain {topic}")
    .param("topic", topic)
).call().content();

Reuse Options

// Define once
private static final ChatOptions CREATIVE_OPTIONS = 
    ChatOptionsBuilder.builder()
        .withTemperature(0.9)
        .withMaxTokens(1000)
        .build();

// Reuse
chatClient.prompt("...").options(CREATIVE_OPTIONS).call().content();

Conditional Configuration

var request = chatClient.prompt();

if (includeContext) {
    request.system("Additional context: " + context);
}

if (needsValidation) {
    request.advisors(validationAdvisor);
}

String response = request.user(query).call().content();

Next Steps

  • Response Handling - Processing responses
  • Working with Advisors - Using interceptors
  • Tool Calling - Function calling patterns

Install with Tessl CLI

npx tessl i tessl/maven-org-springframework-ai--spring-ai-client-chat

docs

guides

building-requests.md

conversation-memory.md

quick-start.md

tool-calling.md

working-with-advisors.md

index.md

tile.json