This repository provides the source code for Large Language Model (LLM) based applications that are used for blog posts, workshop and demos.

Amazon Sagemaker Jumpstart makes it simple to host LLMs as Sagemaker Endpoints enabling uses-cases for inference (text to text generation) and embeddings generation.

The LLM applications in this repo include inference, generating embeddings, question answer (zero-shot and few-shot learning, prompt engineering), retrieval augmented generation (RAG) and domain adapted fine-tuning (coming soon..).

The code in this repo is organized into the following sub-folders, each having its own README.md file.

├── README.md
├── blogs/
├── blogs/rag/
├── blogs/rag/api
├── blogs/rag/app
├── workshop/

• Building a Powerful Question Answering Bot with Amazon SageMaker JumpStart, Amazon OpenSearch, Streamlit, and LangChain: A Step-by-Step Guide

See CONTRIBUTING for more information.

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