This repository project provides Generative Artificial Intelligence engineering notebook samples. The notebooks demonstrate how to deploy Amazon SageMaker JumpStart SDK and Falcon-40B-Instruct model to apply different levels of Large Language Model cutomizations such as decoding strategies and Retrieval-Augmented Generation (RAG).

The following Amazon SageMaker Studio notebooks are available in this repository:

• LLM-Custom-Decoding-Falcon40B-G5.ipynb demonstrates how to generate text using different decoding strategies with Amazon SageMaker JumpStart SDK and Falcon-40B-Instruct model.
• LLM-Custom-Prompting-Falcon40B.ipynb demonstrates how to generate text using prompting engineering techniques with Amazon SageMaker JumpStart SDK and Falcon-40B-Instruct model.
• LLM-Custom-RAG-Kendra-Falcon40B.ipynb demonstrates how to use SageMaker and boto3 SDKs to generate text using the Retrieval-Augmented Generation (RAG) pattern. The notebook implements semantic search using Amazon Kendra enterprise search service. The language model used for text generation is Falcon-40B-Instruct.

To open a Jupyter Notebook using Amazon SageMaker, consider the two steps below:

1. Create or Open an Amazon SageMaker Studio Notebook.
2. Clone this Git Repository in Amazon SageMaker Studio.

See CONTRIBUTING for more information.

This library is licensed under the MIT-0 License. See the LICENSE file.