Official Amazon Bedrock code examples for foundation models, agents, and RAG.
Pre-built Jupyter Notebooks for building generative AI applications on AWS Bedrock
This repository provides reference implementations for interacting with Amazon Bedrock foundation models using Jupyter Notebooks. It suits developers and AI engineers building production workloads on AWS.
It contains modular code examples covering prompt engineering, generative AI agents, custom model imports, and multimodal data handling. You also get specific implementations for Retrieval-Augmented Generation, embeddings, and model observability.
It suits AWS developers and machine learning engineers implementing foundational model features into applications. It does not suit teams looking for a turnkey SaaS application or those not using the AWS ecosystem.
Sample notebooks for all available foundation models on Bedrock.
Examples showing how to build generative AI agents and function calling.
Guides and code for implementing Retrieval-Augmented Generation workflows.
Pathways to transition from proof of concept to production workloads.
The repository code is free to use under its license, but running the examples requires an active AWS account where you pay standard usage fees for Amazon Bedrock foundation model calls.
877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
You need a Jupyter environment, such as Amazon SageMaker notebooks or a self-managed notebook, along with Python and AWS credentials.
Yes, your AWS IAM identity must have explicit permissions to call the Amazon Bedrock service.
See Zekai first in Google