呼び出しモデルを使用して Amazon Bedrock で Meta Llama 2 を呼び出す API

呼び出しモデルAPIを使用してテキストメッセージを送信します。

// Use the native inference API to send a text message to Meta Llama 2.

using System;
using System.IO;
using System.Text.Json;
using System.Text.Json.Nodes;
using Amazon;
using Amazon.BedrockRuntime;
using Amazon.BedrockRuntime.Model;

// Create a Bedrock Runtime client in the AWS Region you want to use.
var client = new AmazonBedrockRuntimeClient(RegionEndpoint.USEast1);

// Set the model ID, e.g., Llama 2 Chat 13B.
var modelId = "meta.llama2-13b-chat-v1";

// Define the prompt for the model.
var prompt = "Describe the purpose of a 'hello world' program in one line.";

// Embed the prompt in Llama 2's instruction format.
var formattedPrompt = $"<s>[INST] {prompt} [/INST]";

//Format the request payload using the model's native structure.
var nativeRequest = JsonSerializer.Serialize(new
{
    prompt = formattedPrompt,
    max_gen_len = 512,
    temperature = 0.5
});

// Create a request with the model ID and the model's native request payload.
var request = new InvokeModelRequest()
{
    ModelId = modelId,
    Body = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(nativeRequest)),
    ContentType = "application/json"
};

try
{
    // Send the request to the Bedrock Runtime and wait for the response.
    var response = await client.InvokeModelAsync(request);

    // Decode the response body.
    var modelResponse = await JsonNode.ParseAsync(response.Body);

    // Extract and print the response text.
    var responseText = modelResponse["generation"] ?? "";
    Console.WriteLine(responseText);
}
catch (AmazonBedrockRuntimeException e)
{
    Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}");
    throw;
}

呼び出しモデルAPIを使用してテキストメッセージを送信します。

// Each model provider has their own individual request and response formats.
// For the format, ranges, and default values for Meta Llama 2 Chat, refer to:
// https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html

type Llama2Request struct {
	Prompt       string  `json:"prompt"`
	MaxGenLength int     `json:"max_gen_len,omitempty"`
	Temperature  float64 `json:"temperature,omitempty"`
}

type Llama2Response struct {
	Generation string `json:"generation"`
}

// Invokes Meta Llama 2 Chat on Amazon Bedrock to run an inference using the input
// provided in the request body.
func (wrapper InvokeModelWrapper) InvokeLlama2(ctx context.Context, prompt string) (string, error) {
	modelId := "meta.llama2-13b-chat-v1"

	body, err := json.Marshal(Llama2Request{
		Prompt:       prompt,
		MaxGenLength: 512,
		Temperature:  0.5,
	})

	if err != nil {
		log.Fatal("failed to marshal", err)
	}

	output, err := wrapper.BedrockRuntimeClient.InvokeModel(ctx, &bedrockruntime.InvokeModelInput{
		ModelId:     aws.String(modelId),
		ContentType: aws.String("application/json"),
		Body:        body,
	})

	if err != nil {
		ProcessError(err, modelId)
	}

	var response Llama2Response
	if err := json.Unmarshal(output.Body, &response); err != nil {
		log.Fatal("failed to unmarshal", err)
	}

	return response.Generation, nil
}

呼び出しモデルAPIを使用してテキストメッセージを送信します。

// Use the native inference API to send a text message to Meta Llama 2.

import org.json.JSONObject;
import org.json.JSONPointer;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.core.exception.SdkClientException;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;

public class Llama2_InvokeModel {

    public static String invokeModel() {

        // Create a Bedrock Runtime client in the AWS Region you want to use.
        // Replace the DefaultCredentialsProvider with your preferred credentials provider.
        var client = BedrockRuntimeClient.builder()
                .credentialsProvider(DefaultCredentialsProvider.create())
                .region(Region.US_EAST_1)
                .build();

        // Set the model ID, e.g., Llama 2 Chat 13B.
        var modelId = "meta.llama2-13b-chat-v1";

        // The InvokeModel API uses the model's native payload.
        // Learn more about the available inference parameters and response fields at:
        // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
        var nativeRequestTemplate = "{ \"prompt\": \"{{instruction}}\" }";

        // Define the prompt for the model.
        var prompt = "Describe the purpose of a 'hello world' program in one line.";

        // Embed the prompt in Llama 2's instruction format.
        var instruction = "<s>[INST] {{prompt}} [/INST]\\n".replace("{{prompt}}", prompt);

        // Embed the instruction in the the native request payload.
        var nativeRequest = nativeRequestTemplate.replace("{{instruction}}", instruction);

        try {
            // Encode and send the request to the Bedrock Runtime.
            var response = client.invokeModel(request -> request
                    .body(SdkBytes.fromUtf8String(nativeRequest))
                    .modelId(modelId)
            );

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

            // Retrieve the generated text from the model's response.
            var text = new JSONPointer("/generation").queryFrom(responseBody).toString();
            System.out.println(text);

            return text;

        } catch (SdkClientException e) {
            System.err.printf("ERROR: Can't invoke '%s'. Reason: %s", modelId, e.getMessage());
            throw new RuntimeException(e);
        }
    }

    public static void main(String[] args) {
        invokeModel();
    }
}

呼び出しモデルAPIを使用してテキストメッセージを送信します。

// Send a prompt to Meta Llama 2 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 2 Chat 13B.
const modelId = "meta.llama2-13b-chat-v1";

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

// Embed the message in Llama 2's prompt format.
const prompt = `<s>[INST] ${userMessage} [/INST]`;

// 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 2 prompt format at:
// https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-2

呼び出しモデルAPIを使用してテキストメッセージを送信します。

    public function invokeLlama2($prompt)
    {
        # The different model providers have individual request and response formats.
        # For the format, ranges, and default values for Meta Llama 2 Chat, refer to:
        # https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html

        $completion = "";

        try {
            $modelId = 'meta.llama2-13b-chat-v1';

            $body = [
                'prompt' => $prompt,
                'temperature' => 0.5,
                'max_gen_len' => 512,
            ];

            $result = $this->bedrockRuntimeClient->invokeModel([
                'contentType' => 'application/json',
                'body' => json_encode($body),
                'modelId' => $modelId,
            ]);

            $response_body = json_decode($result['body']);

            $completion = $response_body->generation;
        } catch (Exception $e) {
            echo "Error: ({$e->getCode()}) - {$e->getMessage()}\n";
        }

        return $completion;
    }

呼び出しモデルAPIを使用してテキストメッセージを送信します。

# Use the native inference API to send a text message to Meta Llama 2.

import boto3
import json

from botocore.exceptions import ClientError

# 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 2 Chat 13B.
model_id = "meta.llama2-13b-chat-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 2's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

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

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

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

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# 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)