Jupyter AI, Integrating AI with Flexibility, but need to set up model api keys first


Jupyter AI now introduces an integration feature with numerous AI model providers. But bear in mind, it’s not free. To get the best out of Jupyter AI, you’ll need to link it up with your desired model provider’s API key or credentials. Below, I’ve summarized the core information for you:

Supported AI Model Providers:

  • AI21:

Package: ai21
API Key Environment Variable: AI21_API_KEY

  • Anthropic:

Package: anthropic
API Key Environment Variable: ANTHROPIC_API_KEY

  • Bedrock (Amazon):

Package: boto3
For access and authentication, visit the Amazon Bedrock Homepage.

  • Cohere:

Package: cohere
API Key Environment Variable: COHERE_API_KEY

  • Hugging Face Hub:

Packages: huggingface_hub, ipywidgets, pillow (the latter is essential for text-to-image models).
API Key Environment Variable: HUGGINGFACEHUB_API_TOKEN
Discover an array of models at Hugging Face’s Models.

  • OpenAI:

Package: openai
API Key Environment Variable: OPENAI_API_KEY
For OpenAI chat models, the package remains openai with the same API key.

  • SageMaker:

Package: boto3
Learn about deploying your model and creating endpoint names in the SageMaker documentation.
Authentication is through boto3.

More instructions about model provides are here


Author: robot learner
Reprint policy: All articles in this blog are used except for special statements CC BY 4.0 reprint policy. If reproduced, please indicate source robot learner !
  TOC