Llama チャット

<dependency>
  <groupId>org.springframework.ai</groupId>
  <artifactId>spring-ai-bedrock-ai-spring-boot-starter</artifactId>
</dependency>

dependencies {
    implementation 'org.springframework.ai:spring-ai-bedrock-ai-spring-boot-starter'
}

ChatResponse response = chatModel.call(
    new Prompt(
        "Generate the names of 5 famous pirates.",
        BedrockLlamaChatOptions.builder()
            .withTemperature(0.4)
        .build()
    ));

spring.ai.bedrock.aws.region=eu-central-1
spring.ai.bedrock.aws.timeout=1000ms
spring.ai.bedrock.aws.access-key=${AWS_ACCESS_KEY_ID}
spring.ai.bedrock.aws.secret-key=${AWS_SECRET_ACCESS_KEY}

spring.ai.bedrock.llama.chat.enabled=true
spring.ai.bedrock.llama.chat.options.temperature=0.8

@RestController
public class ChatController {

    private final BedrockLlamaChatModel chatModel;

    @Autowired
    public ChatController(BedrockLlamaChatModel chatModel) {
        this.chatModel = chatModel;
    }

    @GetMapping("/ai/generate")
    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        return Map.of("generation", chatModel.call(message));
    }

    @GetMapping("/ai/generateStream")
	public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return chatModel.stream(prompt);
    }
}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-bedrock</artifactId>
</dependency>

dependencies {
    implementation 'org.springframework.ai:spring-ai-bedrock'
}

LlamaChatBedrockApi api = new LlamaChatBedrockApi(LlamaChatModel.LLAMA2_70B_CHAT_V1.id(),
	EnvironmentVariableCredentialsProvider.create(),
	Region.US_EAST_1.id(),
	new ObjectMapper(),
	Duration.ofMillis(1000L));

BedrockLlamaChatModel chatModel = new BedrockLlamaChatModel(api,
    BedrockLlamaChatOptions.builder()
        .withTemperature(0.5f)
        .withMaxGenLen(100)
        .withTopP(0.9f).build());

ChatResponse response = chatModel.call(
    new Prompt("Generate the names of 5 famous pirates."));

// Or with streaming responses
Flux<ChatResponse> response = chatModel.stream(
    new Prompt("Generate the names of 5 famous pirates."));

LlamaChatBedrockApi llamaChatApi = new LlamaChatBedrockApi(
        LlamaChatModel.LLAMA3_70B_INSTRUCT_V1.id(),
        Region.US_EAST_1.id(),
        Duration.ofMillis(1000L));

LlamaChatRequest request = LlamaChatRequest.builder("Hello, my name is")
		.withTemperature(0.9f)
		.withTopP(0.9f)
		.withMaxGenLen(20)
		.build();

LlamaChatResponse response = llamaChatApi.chatCompletion(request);

// Streaming response
Flux<LlamaChatResponse> responseStream = llamaChatApi.chatCompletionStream(request);
List<LlamaChatResponse> responses = responseStream.collectList().block();