Bedrock

Jupyter AI Agents supports Amazon Bedrock models.

To use Bedrock models, you'll need to define the following environment variables:

AWS_ACCESS_KEY_ID - The access key for your AWS account.
AWS_SECRET_ACCESS_KEY - The secret key for your AWS account.
AWS_SESSION_TOKEN - The session key for your AWS account. This is only needed when you are using temporary credentials.

Example usage with direct Bedrock integration:

# Prompt agent example with Bedrock
jupyter-ai-agents prompt \
  --url http://localhost:8888 \
  --token MY_TOKEN \
  --model-provider bedrock \
  --model-name anthropic.claude-3-sonnet-20240229-v1:0 \
  --path test.ipynb \
  --input "Create a matplotlib example"