Invoque modelos Mistral AI no Amazon Bedrock usando a API Invoke Model

Use a API Invoke Model para enviar uma mensagem de texto.

        /// <summary>
        /// Asynchronously invokes the Mistral 7B model to run an inference based on the provided input.
        /// </summary>
        /// <param name="prompt">The prompt that you want Mistral 7B 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 Mistral 7B, refer to:
        ///     https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral.html
        /// </remarks>
        public static async Task<List<string?>> InvokeMistral7BAsync(string prompt)
        {
            string mistralModelId = "mistral.mistral-7b-instruct-v0:2";

            AmazonBedrockRuntimeClient client = new(RegionEndpoint.USWest2);

            string payload = new JsonObject()
            {
                { "prompt", prompt },
                { "max_tokens", 200 },
                { "temperature", 0.5 }
            }.ToJsonString();

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

                if (response.HttpStatusCode == System.Net.HttpStatusCode.OK)
                {
                    var results = JsonNode.ParseAsync(response.Body).Result?["outputs"]?.AsArray();

                    generatedText = results?.Select(x => x?["text"]?.GetValue<string?>())?.ToList();
                }
                else
                {
                    Console.WriteLine("InvokeModelAsync failed with status code " + response.HttpStatusCode);
                }
            }
            catch (AmazonBedrockRuntimeException e)
            {
                Console.WriteLine(e.Message);
            }
            return generatedText ?? [];
        }

Use de forma assíncrona a API Invoke Model para enviar uma mensagem de texto.

    /**
     * Asynchronously invokes the Mistral 7B model to run an inference based on the provided input.
     *
     * @param prompt The prompt for Mistral to complete.
     * @return The generated response.
     */
    public static List<String> invokeMistral7B(String prompt) {
        BedrockRuntimeAsyncClient client = BedrockRuntimeAsyncClient.builder()
                .region(Region.US_WEST_2)
                .credentialsProvider(ProfileCredentialsProvider.create())
                .build();

        // Mistral instruct models provide optimal results when
        // embedding the prompt into the following template:
        String instruction = "<s>[INST] " + prompt + " [/INST]";

        String modelId = "mistral.mistral-7b-instruct-v0:2";

        String payload = new JSONObject()
                .put("prompt", instruction)
                .put("max_tokens", 200)
                .put("temperature", 0.5)
                .toString();

        CompletableFuture<InvokeModelResponse> completableFuture = client.invokeModel(request -> request
                        .accept("application/json")
                        .contentType("application/json")
                        .body(SdkBytes.fromUtf8String(payload))
                        .modelId(modelId))
                .whenComplete((response, exception) -> {
                    if (exception != null) {
                        System.out.println("Model invocation failed: " + exception);
                    }
                });

        try {
            InvokeModelResponse response = completableFuture.get();
            JSONObject responseBody = new JSONObject(response.body().asUtf8String());
            JSONArray outputs = responseBody.getJSONArray("outputs");

            return IntStream.range(0, outputs.length())
                    .mapToObj(i -> outputs.getJSONObject(i).getString("text"))
                    .toList();
        } catch (InterruptedException e) {
            Thread.currentThread().interrupt();
            System.err.println(e.getMessage());
        } catch (ExecutionException e) {
            System.err.println(e.getMessage());
        }

        return List.of();
    }

Use a API Invoke Model para enviar uma mensagem de texto.

        /**
         * Invokes the Mistral 7B model to run an inference based on the provided input.
         *
         * @param prompt The prompt for Mistral to complete.
         * @return The generated responses.
         */
        public static List<String> invokeMistral7B(String prompt) {
                BedrockRuntimeClient client = BedrockRuntimeClient.builder()
                        .region(Region.US_WEST_2)
                        .credentialsProvider(ProfileCredentialsProvider.create())
                        .build();

                // Mistral instruct models provide optimal results when
                // embedding the prompt into the following template:
                String instruction = "<s>[INST] " + prompt + " [/INST]";

                String modelId = "mistral.mistral-7b-instruct-v0:2";

                String payload = new JSONObject()
                        .put("prompt", instruction)
                        .put("max_tokens", 200)
                        .put("temperature", 0.5)
                        .toString();

                InvokeModelResponse response = client.invokeModel(request -> request
                        .accept("application/json")
                        .contentType("application/json")
                        .body(SdkBytes.fromUtf8String(payload))
                        .modelId(modelId));

                JSONObject responseBody = new JSONObject(response.body().asUtf8String());
                JSONArray outputs = responseBody.getJSONArray("outputs");

                return IntStream.range(0, outputs.length())
                        .mapToObj(i -> outputs.getJSONObject(i).getString("text"))
                        .toList();

        }

Use a API Invoke Model para enviar uma mensagem de texto.

// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0

import { fileURLToPath } from "url";

import { FoundationModels } from "../../config/foundation_models.js";
import {
  BedrockRuntimeClient,
  InvokeModelCommand,
} from "@aws-sdk/client-bedrock-runtime";

/**
 * @typedef {Object} Output
 * @property {string} text
 *
 * @typedef {Object} ResponseBody
 * @property {Output[]} outputs
 */

/**
 * Invokes a Mistral 7B Instruct model.
 *
 * @param {string} prompt - The input text prompt for the model to complete.
 * @param {string} [modelId] - The ID of the model to use. Defaults to "mistral.mistral-7b-instruct-v0:2".
 */
export const invokeModel = async (
  prompt,
  modelId = "mistral.mistral-7b-instruct-v0:2",
) => {
  // Create a new Bedrock Runtime client instance.
  const client = new BedrockRuntimeClient({ region: "us-east-1" });

  // Mistral instruct models provide optimal results when embedding
  // the prompt into the following template:
  const instruction = `<s>[INST] ${prompt} [/INST]`;

  // Prepare the payload.
  const payload = {
    prompt: instruction,
    max_tokens: 500,
    temperature: 0.5,
  };

  // Invoke the model with the payload and wait for the response.
  const command = new InvokeModelCommand({
    contentType: "application/json",
    body: JSON.stringify(payload),
    modelId,
  });
  const apiResponse = await client.send(command);

  // Decode and return the response.
  const decodedResponseBody = new TextDecoder().decode(apiResponse.body);
  /** @type {ResponseBody} */
  const responseBody = JSON.parse(decodedResponseBody);
  return responseBody.outputs[0].text;
};

// Invoke the function if this file was run directly.
if (process.argv[1] === fileURLToPath(import.meta.url)) {
  const prompt =
    'Complete the following in one sentence: "Once upon a time..."';
  const modelId = FoundationModels.MISTRAL_7B.modelId;
  console.log(`Prompt: ${prompt}`);
  console.log(`Model ID: ${modelId}`);

  try {
    console.log("-".repeat(53));
    const response = await invokeModel(prompt, modelId);
    console.log(response);
  } catch (err) {
    console.log(err);
  }
}

Use a API Invoke Model para enviar uma mensagem de texto.

# Use the native inference API to send a text message to Mistral AI.

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., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

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

# Embed the message in Mistral'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_tokens": 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["outputs"][0]["text"]
print(response_text)