There are more AWS SDK examples available in the AWS Doc SDK Examples
Invoke Meta Llama 3 on Amazon Bedrock using the Invoke Model API
The following code examples show how to send a text message to Meta Llama 3, using the Invoke Model API.
- .NET
-
- AWS SDK for .NET
-
Note
There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository
. Use the Invoke Model API to send a text message.
// Use the native inference API to send a text message to Meta Llama 3. 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.USWest2); // Set the model ID, e.g., Llama 3 70b Instruct. var modelId = "meta.llama3-70b-instruct-v1:0"; // 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 = $@" <|begin_of_text|><|start_header_id|>user<|end_header_id|> {prompt} <|eot_id|> <|start_header_id|>assistant<|end_header_id|> "; //Format the request payload using the model's native structure. var nativeRequest = JsonSerializer.Serialize(new { prompt = formattedPrompt, max_gen_len = 512, temperature = 0.5 }); // Create a request with the model ID and the model's native request payload. var request = new InvokeModelRequest() { ModelId = modelId, Body = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(nativeRequest)), ContentType = "application/json" }; try { // Send the request to the Bedrock Runtime and wait for the response. var response = await client.InvokeModelAsync(request); // Decode the response body. var modelResponse = await JsonNode.ParseAsync(response.Body); // Extract and print the response text. var responseText = modelResponse["generation"] ?? ""; Console.WriteLine(responseText); } catch (AmazonBedrockRuntimeException e) { Console.WriteLine($"ERROR: Can't invoke '{modelId}'. Reason: {e.Message}"); throw; }
-
For API details, see InvokeModel in AWS SDK for .NET API Reference.
-
- Java
-
- SDK for Java 2.x
-
Note
There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository
. Use the Invoke Model API to send a text message.
// Use the native inference API to send a text message to Meta Llama 3. 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 Llama3_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_WEST_2) .build(); // Set the model ID, e.g., Llama 3 70b Instruct. var modelId = "meta.llama3-70b-instruct-v1:0"; // 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 3's instruction format. var instruction = ( "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\\n" + "{{prompt}} <|eot_id|>\\n" + "<|start_header_id|>assistant<|end_header_id|>\\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(); } }
-
For API details, see InvokeModel in AWS SDK for Java 2.x API Reference.
-
- JavaScript
-
- SDK for JavaScript (v3)
-
Note
There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository
. Use the Invoke Model API to send a text message.
// 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 70B Instruct. const modelId = "meta.llama3-70b-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
-
For API details, see InvokeModel in AWS SDK for JavaScript API Reference.
-
- Python
-
- SDK for Python (Boto3)
-
Note
There's more on GitHub. Find the complete example and learn how to set up and run in the AWS Code Examples Repository
. Use the Invoke Model API to send a text message.
# Use the native inference API to send a text message to Meta Llama 3. 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-west-2") # Set the model ID, e.g., Llama 3 70b Instruct. model_id = "meta.llama3-70b-instruct-v1:0" # Define the prompt for the model. prompt = "Describe the purpose of a 'hello world' program in one line." # Embed the prompt in Llama 3's instruction format. formatted_prompt = f""" <|begin_of_text|><|start_header_id|>user<|end_header_id|> {prompt} <|eot_id|> <|start_header_id|>assistant<|end_header_id|> """ # 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)
-
For API details, see InvokeModel in AWS SDK for Python (Boto3) API Reference.
-