As traduções são geradas por tradução automática. Em caso de conflito entre o conteúdo da tradução e da versão original em inglês, a versão em inglês prevalecerá.
Amazon Titan Multimodal Embeddings G1
Esta seção fornece formatos de corpo de solicitação e resposta e exemplos de código para usar a Amazon. Titan Multimodal Embeddings G1
Solicitação e resposta
O corpo da solicitação é passado no body
campo de uma InvokeModelsolicitação.
- Request
-
O corpo da solicitação para a Amazon Titan Multimodal Embeddings G1 inclui os seguintes campos.
{ "inputText": string, "inputImage": base64-encoded string, "embeddingConfig": { "outputEmbeddingLength": 256 | 384 | 1024 } }
Pelo menos um dos campos a seguir é obrigatório. Inclua ambos para gerar um vetor de incorporação que calcule a média dos vetores de incorporação de texto e de incorporação de imagem resultantes.
-
InputText — Insira o texto a ser convertido em incorporações.
-
InputImage — Codifique a imagem que você deseja converter em embeddings em base64 e insira a string nesse campo. Para conferir exemplos de como codificar uma imagem em base64 e decodificar uma string codificada em base64 e transformá-la em uma imagem, consulte os exemplos de código.
O campo a seguir é opcional.
-
EmbeddingConfig — Contém um
outputEmbeddingLength
campo, no qual você especifica um dos seguintes comprimentos para o vetor de incorporações de saída.-
256
-
384
-
1024 (padrão)
-
-
- Response
-
O
body
da resposta contém os seguintes campos.{ "embedding": [float, float, ...], "inputTextTokenCount": int, "message": string }
Os campos são descritos abaixo.
-
incorporação — Uma matriz que representa o vetor de incorporação da entrada que você forneceu.
-
TextTokenContagem de entrada — O número de tokens na entrada de texto.
-
mensagem — Especifica quaisquer erros que ocorram durante a geração.
-
Código de exemplo
Os exemplos a seguir mostram como invocar o Titan Multimodal Embeddings G1 modelo da Amazon com taxa de transferência sob demanda no SDK do Python. Selecione uma guia para ver um exemplo para cada caso de uso.
- Text embeddings
-
Este exemplo mostra como chamar o Titan Multimodal Embeddings G1 modelo da Amazon para gerar incorporações de texto.
# 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
-
Este exemplo mostra como chamar o Titan Multimodal Embeddings G1 modelo da Amazon para gerar incorporações de imagens.
# 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
-
Este exemplo mostra como chamar o Titan Multimodal Embeddings G1 modelo da Amazon para gerar incorporações a partir de uma entrada combinada de texto e imagem. O vetor resultante é a média do vetor de incorporação de texto gerado e do vetor de incorporação de imagem.
# 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()