모델 호출 API를 사용하여 Amazon Bedrock에서 메타 라마 3 호출

Invoke Model API를 사용하여 문자 메시지를 보내세요.

// Send a prompt to Meta Llama 3 and print the response.
public class InvokeModelQuickstart {

    public static void main(String[] args) {

        // Create a Bedrock Runtime client in the AWS Region of your choice.
        var client = BedrockRuntimeClient.builder()
                .region(Region.US_WEST_2)
                .build();

        // Set the model ID, e.g., Llama 3 8B Instruct.
        var modelId = "meta.llama3-8b-instruct-v1:0";

        // Define the user message to send.
        var userMessage = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the message in Llama 3's prompt format.
        var prompt = MessageFormat.format("""
                <|begin_of_text|>
                <|start_header_id|>user<|end_header_id|>
                {0}
                <|eot_id|>
                <|start_header_id|>assistant<|end_header_id|>
                """, userMessage);

        // Create a JSON payload using the model's native structure.
        var request = new JSONObject()
                .put("prompt", prompt)
                // Optional inference parameters:
                .put("max_gen_len", 512)
                .put("temperature", 0.5F)
                .put("top_p", 0.9F);

        // Encode and send the request.
        var response = client.invokeModel(req -> req
                .body(SdkBytes.fromUtf8String(request.toString()))
                .modelId(modelId));

        // Decode the native response body.
        var nativeResponse = new JSONObject(response.body().asUtf8String());

        // Extract and print the response text.
        var responseText = nativeResponse.getString("generation");
        System.out.println(responseText);
    }
}
// Learn more about the Llama 3 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3

Invoke Model API를 사용하여 문자 메시지를 보내세요.

// Send a prompt to Meta Llama 3 and print the response.

import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

// Create a Bedrock Runtime client in the AWS Region of your choice.
const client = new BedrockRuntimeClient({ region: "us-west-2" });

// Set the model ID, e.g., Llama 3 8B Instruct.
const modelId = "meta.llama3-8b-instruct-v1:0";

// Define the user message to send.
const userMessage =
  "Describe the purpose of a 'hello world' program in one sentence.";

// Embed the message in Llama 3's prompt format.
const prompt = `
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
${userMessage}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
`;

// Format the request payload using the model's native structure.
const request = {
  prompt,
  // Optional inference parameters:
  max_gen_len: 512,
  temperature: 0.5,
  top_p: 0.9,
};

// Encode and send the request.
const response = await client.send(
  new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(request),
    modelId,
  }),
);

// Decode the native response body.
/** @type {{ generation: string }} */
const nativeResponse = JSON.parse(new TextDecoder().decode(response.body));

// Extract and print the generated text.
const responseText = nativeResponse.generation;
console.log(responseText);

// Learn more about the Llama 3 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/#special-tokens-used-with-meta-llama-3

Invoke Model API를 사용하여 문자 메시지를 보내세요.

# Use the native inference API to send a text message to Meta Llama 3.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Define the message to send.
user_message = "Describe the purpose of a 'hello world' program in one line."

# Embed the message in Llama 3's prompt format.
prompt = f"""
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
{user_message}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
"""

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generation"]
print(response_text)