Invoke API를 사용한 추론

터미널에서 다음 명령을 실행하고 invoke-model-output.txt라는 파일에서 생성된 응답을 찾습니다.

aws bedrock-runtime invoke-model \
    --model-id amazon.titan-text-premier-v1:0 \
    --body '{
        "inputText": "Describe the purpose of a 'hello world' program in one line.",
        "textGenerationConfig": {
            "maxTokenCount": 512,
            "temperature": 0.5
        }
    }' \
    --cli-binary-format raw-in-base64-out \
    invoke-model-output.txt

다음 Python 코드 예제를 실행하여 텍스트 응답을 생성합니다.

# Use the native inference API to send a text message to Amazon Titan Text.

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., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

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

# Format the request payload using the model's native structure.
native_request = {
    "inputText": prompt,
    "textGenerationConfig": {
        "maxTokenCount": 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["results"][0]["outputText"]
print(response_text)

터미널에서 다음 명령을 실행하고 응답에서 서비스 계층을 검증합니다.

aws bedrock-runtime invoke-model \
    --model-id openai.gpt-oss-120b-1:0 \
    --body '{
        "messages": [
            {
                "role": "user",
                "content": "Describe the purpose of a '\''hello world'\'' program in one line."
            }
        ],
        "max_tokens": 512,
        "temperature": 0.7
    }' \
    --content-type application/json \
    --accept application/json \
    --service-tier priority \
    --cli-binary-format raw-in-base64-out

다음 Python 코드 예제를 실행하여 서비스 계층으로 텍스트 응답을 생성합니다.

import boto3
import json

# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="us-east-1"
)

# Define the model ID and request body
model_id = "openai.gpt-oss-120b-1:0"
body = json.dumps({
    "messages": [
        {
            "role": "user",
            "content": "Describe the purpose of a 'hello world' program in one line."
        }
    ],
    "max_tokens": 512,
    "temperature": 0.7
})

# Make the request with service tier
response = bedrock_runtime.invoke_model(
    modelId=model_id,
    body=body,
    contentType="application/json",
    accept="application/json",
    serviceTier="priority"
)

# Parse and print the response
response_body = json.loads(response["body"])
print(response_body)

터미널에서 다음 명령을 실행하고 invoke-model-output.txt라는 파일에서 생성된 응답을 찾습니다. 이미지를 나타내는 바이트는 응답의 base64 필드에서 찾을 수 있습니다.

aws bedrock-runtime invoke-model \
    --model-id stability.stable-image-core-v1:1 \
    --body '{
        "prompt": "A stylized picture of a cute old steampunk robot.",
        "seed": 0
    }' \
    --cli-binary-format raw-in-base64-out \
    invoke-model-output.txt

다음 Python 코드 예제를 실행하여 이미지를 생성하고 output이라는 폴더에서 결과 stability_1.png 이미지 파일을 찾습니다.

# Use the native inference API to create an image with Amazon Titan Image Generator

import base64
import boto3
import json
import os
import random

# 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., Titan Image Generator G1.
model_id = "amazon.titan-image-generator-v2:0"

# Define the image generation prompt for the model.
prompt = "A stylized picture of a cute old steampunk robot."

# Generate a random seed.
seed = random.randint(0, 2147483647)

# Format the request payload using the model's native structure.
native_request = {
    "taskType": "TEXT_IMAGE",
    "textToImageParams": {"text": prompt},
    "imageGenerationConfig": {
        "numberOfImages": 1,
        "quality": "standard",
        "cfgScale": 8.0,
        "height": 512,
        "width": 512,
        "seed": seed,
    },
}

# 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 the image data.
base64_image_data = model_response["images"][0]

# Save the generated image to a local folder.
i, output_dir = 1, "output"
if not os.path.exists(output_dir):
    os.makedirs(output_dir)
while os.path.exists(os.path.join(output_dir, f"titan_{i}.png")):
    i += 1

image_data = base64.b64decode(base64_image_data)

image_path = os.path.join(output_dir, f"titan_{i}.png")
with open(image_path, "wb") as file:
    file.write(image_data)

print(f"The generated image has been saved to {image_path}")

터미널에서 다음 명령을 실행하고 invoke-model-output.txt라는 파일에서 생성된 응답을 찾습니다. 결과 임베딩은 binary 필드에 있습니다.

aws bedrock-runtime invoke-model \
    --model-id amazon.titan-embed-text-v2:0 \
    --body '{
        "inputText": "What are the different services that you offer?",
        "embeddingTypes": ["binary"]
    }' \
    --cli-binary-format raw-in-base64-out \
    invoke-model-output.txt

다음 Python 코드 예제를 실행하여 제공된 텍스트에 대한 임베딩을 생성합니다.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to generate an embedding with the Amazon Titan Text Embeddings V2 Model
"""

import json
import logging
import boto3


from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_embedding(model_id, body):
    """
    Generate an embedding with the vector representation of a text input using Amazon Titan Text Embeddings G1 on demand.
    Args:
        model_id (str): The model ID to use.
        body (str) : The request body to use.
    Returns:
        response (JSON): The embedding created by the model and the number of input tokens.
    """

    logger.info("Generating an embedding with Amazon Titan Text Embeddings V2 model %s", model_id)

    bedrock = boto3.client(service_name='bedrock-runtime')

    accept = "application/json"
    content_type = "application/json"

    response = bedrock.invoke_model(
        body=body, modelId=model_id, accept=accept, contentType=content_type
    )

    response_body = json.loads(response.get('body').read())

    return response_body


def main():
    """
    Entrypoint for Amazon Titan Embeddings V2 - Text example.
    """

    logging.basicConfig(level=logging.INFO,
                        format="%(levelname)s: %(message)s")

    model_id = "amazon.titan-embed-text-v2:0"
    input_text = "What are the different services that you offer?"


    # Create request body.
    body = json.dumps({
        "inputText": input_text,
        "embeddingTypes": ["binary"]
    })


    try:

        response = generate_embedding(model_id, body)

        print(f"Generated an embedding: {response['embeddingsByType']['binary']}") # returns binary embedding
        print(f"Input text: {input_text}")
        print(f"Input Token count:  {response['inputTextTokenCount']}")

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))

    else:
        print(f"Finished generating an embedding with Amazon Titan Text Embeddings V2 model {model_id}.")


if __name__ == "__main__":
    main()

터미널을 열고 다음을 수행합니다.

다음 Python 스크립트에서 /path/to/image를 실제 이미지의 경로로 바꿉니다. 그런 다음 스크립트를 실행하여 임베딩을 생성합니다.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to generate embeddings from an image with the Amazon Titan Multimodal Embeddings G1 model (on demand).
"""

import base64
import json
import logging
import boto3

from botocore.exceptions import ClientError

class EmbedError(Exception):
    "Custom exception for errors returned by Amazon Titan Multimodal Embeddings G1"

    def __init__(self, message):
        self.message = message

logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_embeddings(model_id, body):
    """
    Generate a vector of embeddings for an image input using Amazon Titan Multimodal Embeddings G1 on demand.
    Args:
        model_id (str): The model ID to use.
        body (str) : The request body to use.
    Returns:
        response (JSON): The embeddings that the model generated, token information, and the
        reason the model stopped generating embeddings.
    """

    logger.info("Generating embeddings with Amazon Titan Multimodal Embeddings G1 model %s", model_id)

    bedrock = boto3.client(service_name='bedrock-runtime')

    accept = "application/json"
    content_type = "application/json"

    response = bedrock.invoke_model(
        body=body, modelId=model_id, accept=accept, contentType=content_type
    )

    response_body = json.loads(response.get('body').read())

    finish_reason = response_body.get("message")

    if finish_reason is not None:
        raise EmbedError(f"Embeddings generation error: {finish_reason}")

    return response_body


def main():
    """
    Entrypoint for Amazon Titan Multimodal Embeddings G1 example.
    """

    logging.basicConfig(level=logging.INFO,
                        format="%(levelname)s: %(message)s")

    # Read image from file and encode it as base64 string.
    with open("/path/to/image", "rb") as image_file:
        input_image = base64.b64encode(image_file.read()).decode('utf8')

    model_id = 'amazon.titan-embed-image-v1'
    output_embedding_length = 256

    # Create request body.
    body = json.dumps({
        "inputImage": input_image,
        "embeddingConfig": {
            "outputEmbeddingLength": output_embedding_length
        }
    })


    try:

        response = generate_embeddings(model_id, body)

        print(f"Generated image embeddings of length {output_embedding_length}: {response['embedding']}")

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))
        
    except EmbedError as err:
        logger.error(err.message)
        print(err.message)

    else:
        print(f"Finished generating image embeddings with Amazon Titan Multimodal Embeddings G1 model {model_id}.")


if __name__ == "__main__":
    main()

다음 예제에서는 Anthropic Claude 3 Haiku 모델을 사용하여 주어진 이미지와 이미지의 내용을 묻는 텍스트 프롬프트로 응답을 생성합니다. 터미널을 열고 다음을 수행합니다.

다음 Python 스크립트에서 스크립트를 실행하기 전에 /path/to/image.png를 실제 이미지 경로로 바꿉니다.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to run a multimodal prompt with Anthropic Claude (on demand) and InvokeModel.
"""

import json
import logging
import base64
import boto3

from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def run_multi_modal_prompt(bedrock_runtime, model_id, messages, max_tokens):
    """
    Invokes a model with a multimodal prompt.
    Args:
        bedrock_runtime: The Amazon Bedrock boto3 client.
        model_id (str): The model ID to use.
        messages (JSON) : The messages to send to the model.
        max_tokens (int) : The maximum  number of tokens to generate.
    Returns:
        None.
    """



    body = json.dumps(
        {
            "anthropic_version": "bedrock-2023-05-31",
            "max_tokens": max_tokens,
            "messages": messages
        }
    )

    response = bedrock_runtime.invoke_model(
        body=body, modelId=model_id)
    response_body = json.loads(response.get('body').read())

    return response_body


def main():
    """
    Entrypoint for Anthropic Claude multimodal prompt example.
    """

    try:

        bedrock_runtime = boto3.client(service_name='bedrock-runtime')

        model_id = 'anthropic.claude-3-sonnet-20240229-v1:0'
        max_tokens = 1000
        input_text = "What's in this image?"
        input_image = "/path/to/image" # Replace with actual path to image file
 
        # Read reference image from file and encode as base64 strings.
        image_ext = input_image.split(".")[-1]
        with open(input_image, "rb") as image_file:
            content_image = base64.b64encode(image_file.read()).decode('utf8')

        message = {
            "role": "user",
            "content": [
                {
                    "type": "image", 
                    "source": {
                        "type": "base64",
                        "media_type": f"image/{image_ext}", 
                        "data": content_image
                    }
                },
                {
                    "type": "text", 
                    "text": input_text
                }
            ]
        }

    
        messages = [message]

        response = run_multi_modal_prompt(
            bedrock_runtime, model_id, messages, max_tokens)
        print(json.dumps(response, indent=4))

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occurred: " +
              format(message))


if __name__ == "__main__":
    main()

터미널을 열고 다음 명령을 실행하여 s3://amzn-s3-demo-bucket/video.mp4를 비디오의 실제 S3 위치로 바꿉니다.

aws bedrock-runtime invoke-model \
    --model-id amazon.nova-lite-v1:0 \
    --body '{
        "messages": [          
            {               
                "role": "user",
                "content": [      
                    {                       
                        "video": {     
                            "format": "mp4",   
                            "source": {
                                "s3Location": {
                                    "uri": "s3://amzn-s3-demo-bucket/video.mp4"
                                }
                            }
                        }                                    
                    },
                    {
                        "text": "What happens in this video?"
                    }
                ]
            }                              
        ]                  
    }' \
    --cli-binary-format raw-in-base64-out \
    invoke-model-output.txt

현재 폴더의 invoke-model-output.txt 파일에서 출력을 찾습니다.

다음 Python 스크립트에서 s3://amzn-s3-demo-bucket/video.mp4를 비디오의 실제 S3 위치로 바꿉니다. 그런 다음 이 스크립트를 실행합니다.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to run a multimodal prompt with Nova Lite (on demand) and InvokeModel.
"""

import json
import logging
import base64
import boto3

from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def run_multi_modal_prompt(bedrock_runtime, model_id, messages, max_tokens):
    """
    Invokes a model with a multimodal prompt.
    Args:
        bedrock_runtime: The Amazon Bedrock boto3 client.
        model_id (str): The model ID to use.
        messages (JSON) : The messages to send to the model.
        max_tokens (int) : The maximum  number of tokens to generate.
    Returns:
        None.
    """

    body = json.dumps(
        {
            "messages": messages,
            "inferenceConfig": {
                "maxTokens": max_tokens
            }
        }
    )

    response = bedrock_runtime.invoke_model(
        body=body, modelId=model_id)
    response_body = json.loads(response.get('body').read())

    return response_body


def main():
    """
    Entrypoint for Nova Lite video prompt example.
    """

    try:

        bedrock_runtime = boto3.client(service_name='bedrock-runtime')

        model_id = "amazon.nova-lite-v1:0"
        max_tokens = 1000
        input_video_s3_uri = "s3://amzn-s3-demo-bucket/video.mp4" # Replace with real S3 URI
        video_ext = input_video_s3_uri.split(".")[-1]
        input_text = "What happens in this video?"

        message = {
            "role": "user",
            "content": [
                {
                    "video": {
                        "format": video_ext,
                        "source": {
                            "s3Location": {
                                "uri": input_video_s3_uri
                            }
                        }
                    }
                },
                {
                    "text": input_text
                }
            ]
        }

    
        messages = [message]

        response = run_multi_modal_prompt(
            bedrock_runtime, model_id, messages, max_tokens)
        print(json.dumps(response, indent=4))

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))


if __name__ == "__main__":
    main()

해결 방법:

다음 Python 스크립트에서 /path/to/video.mp4를 실제 비디오 경로로 바꿉니다. 그런 다음 이 스크립트를 실행합니다.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to run a multimodal prompt with Nova Lite (on demand) and InvokeModel.
"""

import json
import logging
import base64
import boto3

from botocore.exceptions import ClientError


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def run_multi_modal_prompt(bedrock_runtime, model_id, messages, max_tokens):
    """
    Invokes a model with a multimodal prompt.
    Args:
        bedrock_runtime: The Amazon Bedrock boto3 client.
        model_id (str): The model ID to use.
        messages (JSON) : The messages to send to the model.
        max_tokens (int) : The maximum  number of tokens to generate.
    Returns:
        None.
    """

    body = json.dumps(
        {
            "messages": messages,
            "inferenceConfig": {
                "maxTokens": max_tokens
            }
        }
    )

    response = bedrock_runtime.invoke_model(
        body=body, modelId=model_id)
    response_body = json.loads(response.get('body').read())

    return response_body


def main():
    """
    Entrypoint for Nova Lite video prompt example.
    """

    try:

        bedrock_runtime = boto3.client(service_name='bedrock-runtime')

        model_id = "amazon.nova-lite-v1:0"
        max_tokens = 1000
        input_video = "/path/to/video.mp4" # Replace with real path to video
        video_ext = input_video.split(".")[-1]
        input_text = "What happens in this video?"

        # Read reference video from file and encode as base64 string.
        with open(input_video, "rb") as video_file:
            content_video = base64.b64encode(video_file.read()).decode('utf8')\

        message = {
            "role": "user",
            "content": [
                {
                    "video": {
                        "format": video_ext,
                        "source": {
                            "bytes": content_video
                        }
                    }
                },
                {
                    "text": input_text
                }
            ]
        }

    
        messages = [message]

        response = run_multi_modal_prompt(
            bedrock_runtime, model_id, messages, max_tokens)
        print(json.dumps(response, indent=4))

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))


if __name__ == "__main__":
    main()