Exemplos do Amazon Bedrock usando o SDK para Python (Boto3)

"""
Lists the available Amazon Bedrock models.
"""
import logging
import json
import boto3


from botocore.exceptions import ClientError


logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)


def list_foundation_models(bedrock_client):
    """
    Gets a list of available Amazon Bedrock foundation models.

    :return: The list of available bedrock foundation models.
    """

    try:
        response = bedrock_client.list_foundation_models()
        models = response["modelSummaries"]
        logger.info("Got %s foundation models.", len(models))
        return models

    except ClientError:
        logger.error("Couldn't list foundation models.")
        raise


def main():
    """Entry point for the example. Uses the AWS SDK for Python (Boto3)
    to create an Amazon Bedrock client. Then lists the available Bedrock models
    in the region set in the callers profile and credentials.
    """

    bedrock_client = boto3.client(service_name="bedrock")

    fm_models = list_foundation_models(bedrock_client)
    for model in fm_models:
        print(f"Model: {model['modelName']}")
        print(json.dumps(model, indent=2))
        print("---------------------------\n")

    logger.info("Done.")


if __name__ == "__main__":
    main()

Obtenha detalhes de um modelo de base.

    def get_foundation_model(self, model_identifier):
        """
        Get details about an Amazon Bedrock foundation model.

        :return: The foundation model's details.
        """

        try:
            return self.bedrock_client.get_foundation_model(
                modelIdentifier=model_identifier
            )["modelDetails"]
        except ClientError:
            logger.error(
                f"Couldn't get foundation models details for {model_identifier}"
            )
            raise

Listar os modelos de base do Amazon Bedrock disponíveis.

    def list_foundation_models(self):
        """
        List the available Amazon Bedrock foundation models.

        :return: The list of available bedrock foundation models.
        """

        try:
            response = self.bedrock_client.list_foundation_models()
            models = response["modelSummaries"]
            logger.info("Got %s foundation models.", len(models))
            return models

        except ClientError:
            logger.error("Couldn't list foundation models.")
            raise

O cenário de encadeamento de prompts do Amazon Bedrock Sem Servidor demonstra como o AWS Step Functions, o Amazon Bedrock e a documentação https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html podem ser usados para criar e orquestrar aplicações de IA generativa complexas, sem servidor e altamente escaláveis. Ele contém os seguintes exemplos de trabalho:

Para obter o código-fonte completo e as instruções sobre como configurar e executar, consulte o projeto completo no GitHub.