This package provides functionality developed to simplify interfacing with the Cohere models via AWS SageMaker Marketplace in Python 3.
The package can be installed with pip:
pip install --upgrade cohere-sagemakerInstall from source:
python setup.py installTo use this library, you need to configure your AWS credentials. You can do this by running aws configure. Once that's set up, you can use the library like this:
from cohere_sagemaker import Client
client = Client(endpoint_name='my-cohere-endpoint')
# generate prediction for a prompt
response = client.generate(
prompt="Tell me a story about",
max_tokens=20)
print(response.generations[0].text)
# a time when you had to make a difficult decision. What did you doNote: by default we assume region configured in AWS CLI (aws configure get region), to override use region_name parameter, e.g.
client = Client(endpoint_name='my-cohere-endpoint', region_name='us-east-1')More detailed examples can be found in the Jupyter notebook.