Amazon Titan Multimodal Embeddings G1 - Amazon Bedrock

Les traductions sont fournies par des outils de traduction automatique. En cas de conflit entre le contenu d'une traduction et celui de la version originale en anglais, la version anglaise prévaudra.

Amazon Titan Multimodal Embeddings G1

Cette section fournit des formats de corps de demande et de réponse ainsi que des exemples de code pour l'utilisation d'AmazonTitan Multimodal Embeddings G1.

Demande et réponse

Le corps de la demande est transmis dans le body champ d'une InvokeModeldemande.

Request

Le corps de la demande pour Amazon Titan Multimodal Embeddings G1 inclut les champs suivants.

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

Au moins l'un des champs suivants est obligatoire. Incluez les deux pour générer un vecteur d'intégration qui fait la moyenne des vecteurs d'intégration de texte et d'image résultants.

  • inputText— Entrez le texte à convertir en éléments incorporés.

  • inputImage— Codez l'image que vous souhaitez convertir en intégrations en base64 et entrez la chaîne dans ce champ. Pour des exemples de codage d’une image en base64, de décodage d’une chaîne codée en base64 et de transformation de celle-ci en image, consultez les exemples de code.

Le champ suivant est facultatif.

  • embeddingConfig— Contient un outputEmbeddingLength champ dans lequel vous spécifiez l'une des longueurs suivantes pour le vecteur d'intégration en sortie.

    • 256

    • 384

    • 1024 (par défaut)

Response

La body réponse contient les champs suivants.

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

Les champs sont décrits ci-dessous.

  • incorporation — Tableau qui représente le vecteur d'intégration de l'entrée que vous avez fournie.

  • inputTextTokenNombre : nombre de jetons dans le texte saisi.

  • message — Spécifie les erreurs qui se produisent lors de la génération.

Exemple de code

Les exemples suivants montrent comment invoquer le Titan Multimodal Embeddings G1 modèle Amazon avec un débit à la demande en PythonSDK. Sélectionnez un onglet pour voir un exemple de chaque cas d’utilisation.

Text embeddings

Cet exemple montre comment appeler le Titan Multimodal Embeddings G1 modèle Amazon pour générer des intégrations de texte.

# 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

Cet exemple montre comment appeler le Titan Multimodal Embeddings G1 modèle Amazon pour générer des intégrations d'images.

# 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

Cet exemple montre comment appeler le Titan Multimodal Embeddings G1 modèle Amazon pour générer des intégrations à partir d'une saisie combinée de texte et d'image. Le vecteur obtenu est la moyenne du vecteur d'intégration de texte généré et du vecteur d'intégration d'image.

# 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()