使用调用模型 API 在 Amazon Bedrock 上调用 Meta Llama 2

使用调用模型 API 发送短信。

        /// <summary>
        /// Asynchronously invokes the Meta Llama 2 Chat model to run an inference based on the provided input.
        /// </summary>
        /// <param name="prompt">The prompt that you want Llama 2 to complete.</param>
        /// <returns>The inference response from the model</returns>
        /// <remarks>
        /// 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
        /// </remarks>
        public static async Task<string> InvokeLlama2Async(string prompt)
        {
            string llama2ModelId = "meta.llama2-13b-chat-v1";

            AmazonBedrockRuntimeClient client = new(RegionEndpoint.USEast1);

            string payload = new JsonObject()
            {
                { "prompt", prompt },
                { "max_gen_len", 512 },
                { "temperature", 0.5 },
                { "top_p", 0.9 }
            }.ToJsonString();

            string generatedText = "";
            try
            {
                InvokeModelResponse response = await client.InvokeModelAsync(new InvokeModelRequest()
                {
                    ModelId = llama2ModelId,
                    Body = AWSSDKUtils.GenerateMemoryStreamFromString(payload),
                    ContentType = "application/json",
                    Accept = "application/json"
                });

                if (response.HttpStatusCode == System.Net.HttpStatusCode.OK)
                {
                    return JsonNode.ParseAsync(response.Body)
                        .Result?["generation"]?.GetValue<string>() ?? "";
                }
                else
                {
                    Console.WriteLine("InvokeModelAsync failed with status code " + response.HttpStatusCode);
                }
            }
            catch (AmazonBedrockRuntimeException e)
            {
                Console.WriteLine(e.Message);
            }
            return generatedText;
        }

使用调用模型 API 发送短信。

// 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(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(context.TODO(), &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
}

使用调用模型 API 发送短信。

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

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

        // Embed the message in Llama 2's prompt format.
        var prompt = "<s>[INST] " + userMessage + " [/INST]";

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

使用调用模型 API 发送短信。

// 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

使用调用模型 API 发送短信。

    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;
    }

使用调用模型 API 发送短信。

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

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

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

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

# 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)