Cohere Command models

You make inference requests to an Cohere Command model with InvokeModel or InvokeModelWithResponseStream (streaming). You need the model ID for the model that you want to use. To get the model ID, see Amazon Bedrock model IDs.

Request and Response

Code example

This examples shows how to call the Cohere Command model.

# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to generate text using a Cohere model.
"""
import json
import logging
import boto3


from botocore.exceptions import ClientError

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


def generate_text(model_id, body):
    """
    Generate text using a Cohere model.
    Args:
        model_id (str): The model ID to use.
        body (str) : The reqest body to use.
    Returns:
        dict: The response from the model.
    """

    logger.info("Generating text with Cohere model %s", model_id)

    accept = 'application/json'
    content_type = 'application/json'

    bedrock = boto3.client(service_name='bedrock-runtime')

    response = bedrock.invoke_model(
        body=body,
        modelId=model_id,
        accept=accept,
        contentType=content_type
    )

    logger.info("Successfully generated text with Cohere model %s", model_id)

    return response


def main():
    """
    Entrypoint for Cohere example.
    """

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

    model_id = 'cohere.command-text-v14'
    prompt = """Summarize this dialogue: 
"Customer: Please connect me with a support agent.
AI: Hi there, how can I assist you today?
Customer: I forgot my password and lost access to the email affiliated to my account. Can you please help me?
AI: Yes of course. First I'll need to confirm your identity and then I can connect you with one of our support agents.
"""
    try:
        body = json.dumps({
            "prompt": prompt,
            "max_tokens": 200,
            "temperature": 0.6,
            "p": 1,
            "k": 0,
            "num_generations": 2,
            "return_likelihoods": "GENERATION"
        })
        response = generate_text(model_id=model_id,
                                 body=body)

        response_body = json.loads(response.get('body').read())
        generations = response_body.get('generations')

        for index, generation in enumerate(generations):

            print(f"Generation {index + 1}\n------------")
            print(f"Text:\n {generation['text']}\n")
            if 'likelihood' in generation:
                print(f"Likelihood:\n {generation['likelihood']}\n")
            
            print(f"Reason: {generation['finish_reason']}\n\n")

    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 text with Cohere model {model_id}.")


if __name__ == "__main__":
    main()