Amazon Titan 內嵌文字 - Amazon Bedrock
請求和回應範例程式碼

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 內嵌文字

Titan Embeddings G1 - Text 不支援使用推論參數。下列各節詳細說明請求和回應格式，並提供程式碼範例。

請求和回應

請求內文會在InvokeModel請求的 body 欄位中傳遞。

V2 Request

inputText 參數為必填。標準化和維度參數為選用。

  • inputText – 輸入要轉換為內嵌的文字。

  • 標準化 – （選用） 指示是否標準化輸出內嵌的旗標。預設為 true。

  • 維度 – （選用） 輸出內嵌應具有的維度。接受下列值：1024 （預設）、512、256。

  • embeddingTypes – （選用） 接受包含「浮點」、「二進位」或兩者的清單。預設為 float。

{
    "inputText": string,
    "dimensions": int,
    "normalize": boolean,
    "embeddingTypes": list
}
V2 Response

這些 欄位如下所述。

  • 內嵌 – 表示您提供的輸入內嵌向量的陣列。這一律是類型 float。

  • inputTextToken計數 – 輸入中的權杖數目。

  • embeddingsByType – 內嵌清單的字典或地圖。根據輸入， 會列出「浮點」、「二進位」或兩者。

    • 範例："embeddingsByType": {"binary": [int,..], "float": [float,...]}

    • 此欄位一律會顯示。即使您未在輸入embeddingTypes中指定 ，仍然會有「浮點」。範例："embeddingsByType": {"float": [float,...]}

{
    "embedding": [float, float, ...],
    "inputTextTokenCount": int,
    "embeddingsByType": {"binary": [int,..], "float": [float,...]}
}
G1 Request

唯一可用的欄位是 inputText，其中您可以包含要轉換為內嵌的文字。

{
    "inputText": string
}
G1 Response

回應body的 包含下列欄位。

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

這些 欄位如下所述。

  • 內嵌 – 表示您提供的輸入內嵌向量的陣列。

  • inputTextToken計數 – 輸入中的權杖數目。

範例程式碼

下列範例示範如何呼叫 Amazon Titan 內嵌模型來產生內嵌。選取與您正在使用的模型對應的索引標籤：

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

import json
import logging
import boto3


from botocore.exceptions import ClientError


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 Embeddings G1 - Text 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 embeddings with Amazon Titan Embeddings G1 - Text 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 G1 - Text example.
    """

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

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


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


    try:

        response = generate_embeddings(model_id, body)

        print(f"Generated embeddings: {response['embedding']}")
        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 embeddings with Amazon Titan Embeddings G1 - Text model {model_id}.")


if __name__ == "__main__":
    main()
Amazon Titan Text Embeddings V2

使用 時 Titan Text Embeddings V2，如果 embeddingTypes僅包含 ，則 embedding 欄位不會在回應中binary。

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to generate embeddings 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_embeddings(model_id, body):
    """
    Generate a vector of embeddings for 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 embeddings 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_embeddings(model_id, body)

        print(f"Generated embeddings: {response['embeddingByTypes']['binary']}") # returns binary embedding
        # print(f"Generated embeddings: {response['embedding']}") NOTE:"embedding" field is not in "response".
        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 embeddings with Amazon Titan Text Embeddings V2 model {model_id}.")


if __name__ == "__main__":
    main()