Amazon Titan Multimodal Embeddings G1

Badan permintaan untuk Amazon Titan Multimodal Embeddings G1 termasuk bidang-bidang berikut.

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

Setidaknya satu dari bidang berikut diperlukan. Sertakan keduanya untuk menghasilkan vektor embeddings yang rata-rata menghasilkan penyematan teks dan vektor penyematan gambar.

Bidang berikut adalah opsional.

Respons berisi bidang-bidang berikut. body

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

Bidang dijelaskan di bawah ini.

Contoh ini menunjukkan cara memanggil Amazon Titan Multimodal Embeddings G1 model untuk menghasilkan penyematan teks.

# 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()

Contoh ini menunjukkan cara memanggil Amazon Titan Multimodal Embeddings G1 model untuk menghasilkan embeddings gambar.

# 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()

Contoh ini menunjukkan cara memanggil Amazon Titan Multimodal Embeddings G1 model untuk menghasilkan embeddings dari teks gabungan dan input gambar. Vektor yang dihasilkan adalah rata-rata vektor penyematan teks yang dihasilkan dan vektor penyematan gambar.

# 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()