Las traducciones son generadas a través de traducción automática. En caso de conflicto entre la traducción y la version original de inglés, prevalecerá la version en inglés.
Texto incrustado de Amazon Titan
Titan Embeddings G1 - Textno admite el uso de parámetros de inferencia. En las siguientes secciones se detallan los formatos de solicitud y respuesta y se proporciona un ejemplo de código.
Solicitud y respuesta
El cuerpo de la solicitud se pasa al body
campo de una InvokeModelsolicitud.
- V2 Request
-
El parámetro inputText es obligatorio. Los parámetros de normalización y dimensiones son opcionales.
-
InputText: introduzca texto para convertirlo en incrustaciones.
-
normalizar: indicador que indica si se deben normalizar o no las incrustaciones de salida. El valor predeterminado es true (verdadero).
-
dimensiones: el número de dimensiones que deben tener las incrustaciones de salida. Se aceptan los siguientes valores: 1024 (predeterminado), 512, 256.
{ "inputText": string, "dimensions": int, "normalize": boolean }
-
- V2 Response
-
Los campos se describen a continuación.
-
incrustación: matriz que representa el vector de incrustaciones de la entrada que ha proporcionado.
-
entradaTextTokenCount : el número de símbolos de la entrada.
{ "embedding": [float, float, ...], "inputTextTokenCount": int }
-
- G1 Request
-
El único campo disponible es el
inputText
siguiente: en el que se puede incluir texto para convertirlo en incrustaciones.{ "inputText": string }
- G1 Response
-
El
body
de la respuesta contiene los siguientes campos.{ "embedding": [float, float, ...], "inputTextTokenCount": int }
Los campos se describen a continuación.
-
incrustación: matriz que representa el vector de incrustaciones de la entrada que proporcionó.
-
TextTokenRecuento de entradas: el número de símbolos de la entrada.
-
Código de ejemplo
Los siguientes ejemplos muestran cómo llamar al modelo Amazon Titan Embeddings para generar incrustaciones. Seleccione la pestaña que corresponda al modelo que está utilizando:
- 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
-
# 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, "dimensions": 512, "normalize": True }) 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 Text Embeddings V2 model {model_id}.") if __name__ == "__main__": main() </programlisting> <para><emphasis role="bold">Configure your accuracy-cost tradeoff as you go</emphasis></para> <para>While normalization is available via API customers can also reduce the embedding dimension after generating the embeddings allowing them to tradeoff between accuracy and cost as their need evolve. This empower customers to generate 1024-dim index embeddings, store them in low-cost storage options such as S3 and load their 1024, 512 or 256 dimension version in their favorite vector DB as they go. </para> <para>To reduce a given embedding from 1024 to 256 dimensions you can use the following example logic:</para> <programlisting language="json">import numpy as np from numpy import linalg def normalize_embedding(embedding: np.Array): ''' Args: embedding: Unnormlized 1D/2D numpy array - 1D: (emb_dim) - 2D: (batch_size, emb_dim) Return: np.array: Normalized 1D/2D numpy array ''' return embedding/linalg.norm(embedding, dim=-1, keep_dim=True) def reduce_emb_dim(embedding: np.Array, target_dim:int, normalize:bool=True) -> np.Array: ''' Args: embedding: Unnormlized 1D/2D numpy array. Expected shape: - 1D: (emb_dim) - 2D: (batch_size, emb_dim) target_dim: target dimension to reduce the embedding to Return: np.array: Normalized 1D numpy array ''' smaller_embedding = embedding[..., :target_dim] if normalize: smaller_embedding = normalize_embedding(smaller_embedding) return smaller_embedding if __name__ == '__main__': embedding = # bedrock client call reduced_embedding = # bedrock client call with dim=256 post_reduction_embeddings = reduce_emb_dim(np.array(embeddings), dim=256) print(linalg.norm(np.array(reduced_embedding) - post_reduction_embeddings))