This Jupyter notebook demonstrates how to leverage AWS services and generative AI to enhance healthcare solutions. It outlines the process of creating a serverless system that provides custom medical recommendations, showcasing the practical application and benefits of integrating generative AI models in healthcare.
Before you begin, ensure you have the following pre-requisites:
- An AWS account
- Access to Claude 3 and Titan Embeddings models (you can request access through the AWS console)
- A SageMaker Studio Domain
To set up the project environment, clone this repository in a terminal inside SageMaker's Jupyter Lab:
git clone https://github.com/duartemoura/Dr.-Claude.gitTo run the notebook:
- Launch your SageMaker Studio Domain
- Create JupyterLab space if you don't have one already
- Start JupyterLab
- Open the llm_kb_email.ipynb file
- Choose a kernel - Python3 (ipykernel)
- Follow the instructions within the notebook to execute the cells
Some of the code used in this notebook was taken from the AWS Bedrock Workshop GitHub repository.