Amazon Titan Multimodal Embeddings G1

本节提供请求和响应正文格式以及使用 Amazon Titan Multimodal Embeddings G1 的代码示例。

请求和回应

请求正文在InvokeModel请求的body字段中传递。

Request

Amazon 的请求正文Titan Multimodal Embeddings G1包括以下字段。

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

以下字段中至少有一个是必填字段。同时包含两者以生成对生成的文本嵌入求平均值的嵌入向量和图像嵌入向量。

• InputText-输入要转换为嵌入的文本。

• inputImag e — 在 base64 中对要转换为嵌入的图像进行编码，然后在此字段中输入字符串。有关如何将图像编码为 base64 以及如何对 base64 编码的字符串进行解码并将其转换为图像的示例，请参阅代码示例。

以下字段是可选字段。

• embeddingConfig — 包含一个outputEmbeddingLength字段，在该字段中，您可以为输出嵌入向量指定以下长度之一。

  • 256

  • 384

  • 1024（默认值）

Response

响应body的包含以下字段。

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

字段如下所述。

• embedding — 一个数组，它表示您提供的输入的嵌入向量。

• inpu TextToken t Count — 文本输入中的标记数。

• mes sage-指定生成过程中发生的任何错误。

代码示例

以下示例演示如何在 Python 软件开发工具包中使用按需吞吐量调用 Amazon Titan Multimodal Embeddings G1 模型。选择一个选项卡查看每个用例的示例。

Text embeddings

此示例说明如何调用 Amazon Titan Multimodal Embeddings G1 模型来生成文本嵌入。

# 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

此示例说明如何调用 Amazon Titan Multimodal Embeddings G1 模型来生成图像嵌入。

# 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

此示例说明如何调用 Amazon Titan Multimodal Embeddings G1 模型，通过组合的文本和图像输入生成嵌入内容。生成的向量是生成的文本嵌入向量和图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()