Amazon Titan Multimodal Embeddings G1 - Amazon Bedrock
請求與回應範例程式碼

本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

Amazon Titan Multimodal Embeddings G1

本節提供使用 Amazon Titan Multimodal Embeddings G1 的請求和回應內文格式與程式碼範例。

請求與回應

請求內文在 InvokeModel 請求的 body 欄位中傳遞。

Request

Amazon Titan Multimodal Embeddings G1 的請求內文包含下列欄位。

{
    "inputText": string,
    "inputImage": base64-encoded string,
    "embeddingConfig": {
        "outputEmbeddingLength": 256 | 384 | 1024
    }
}

至少需要下列其中一個欄位。同時包含兩者可產生嵌入向量，該向量會將產生的文本嵌入和影像嵌入向量加以平均。

  • inputText – 輸入要轉換為嵌入的文字。

  • inputImage – 以 base64 將您要轉換為嵌入的影像編碼，並在此欄位中輸入字串。有關如何將影像編碼為 base64 並解碼 base64 編碼的字串，再將其轉換為影像的範例，請參閱程式碼範例。

下列欄位為選用。

  • embeddingConfig – 包含 outputEmbeddingLength 欄位，您可以在其中為輸出嵌入向量指定下列其中一個長度。

    • 256

    • 384

    • 1024 (預設)

Response

回應的 body 包含下列欄位。

{
    "embedding": [float, float, ...],
    "inputTextTokenCount": int,
    "message": string
}

這些欄位如下所述。

  • embedding – 代表您所提供輸入的嵌入向量陣列。

  • inputTextTokenCount – 文字輸入中的字符數量。

  • message – 指定產生期間發生的任何錯誤。

範例程式碼

下列範例展示如何在 Python SDK 中以隨需輸送量調用 Amazon Titan Multimodal Embeddings G1 模型。選取標籤以檢視每個使用案例的範例。

Text embeddings

此範例展示如何呼叫 Amazon Titan Multimodal Embeddings G1 模型來產生文本嵌入。

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

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 a text 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")

    model_id = "amazon.titan-embed-image-v1"
    input_text = "What are the different services that you offer?"
    output_embedding_length = 256

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


    try:

        response = generate_embeddings(model_id, body)

        print(f"Generated text embeddings of length {output_embedding_length}: {response['embedding']}")
        print(f"Input text 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))
        
    except EmbedError as err:
        logger.error(err.message)
        print(err.message)

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


if __name__ == "__main__":
    main()
Image embeddings

此範例展示如何呼叫 Amazon Titan Multimodal Embeddings G1 模型來產生影像嵌入。

# 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()
Text and image embeddings

此範例示範如何呼叫 Amazon Titan Multimodal Embeddings G1 模型，以從合併的文字和影像輸入產生嵌入。產生的向量是產生的文本嵌入向量和影像嵌入向量的平均值。

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to generate embeddings from an image and accompanying text 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 a combined text and 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")

    model_id = "amazon.titan-embed-image-v1"
    input_text = "A family eating dinner"
    # 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')
    output_embedding_length = 256

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


    try:

        response = generate_embeddings(model_id, body)

        print(f"Generated embeddings of length {output_embedding_length}: {response['embedding']}")
        print(f"Input text 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))
        
    except EmbedError as err:
        logger.error(err.message)
        print(err.message)

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


if __name__ == "__main__":
    main()