Best practices to build generative AI applications on AWS | AWS Machine Learning BlogAmazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon via a single API.
Amazon SageMaker is a fully managed service that makes it straightforward to build, train, and deploy ML models.
Amazon SageMaker JumpStart offers an ML hub where you can explore, train, and deploy a wide selection of public FM
Common generative AI approaches
Prompt engineering:
Zero-shot prompting, Few-shot prompting, Chain-of-thought prompting
Retrieval Augmented Generation (RAG) allows you to customize a model’s responses when you want the model to consider new knowledge or up-to-date information.
Agents
Frameworks like
LangChain and certain FMs such as Claude models provide function-calling capabilities to interact with APIs and tools. However,
Amazon Bedrock Agents, a new and fully managed AI capability from AWS, aims to make it more straightforward for developers to build applications using next-generation FMs.
Model customization
Fine-tuning
Continued pre-training
Retraining or training from scratch
