Generative AI on Aws: Building Context-Aware Multimodal Reasoning Applications (Paperback)

Companies today are moving rapidly to integrate generative AI into their products and services. But there's a great deal of hype (and misunderstanding) about the impact and promise of this technology. In this book, Chris Fregly, Antje Barth, and Shelbee Eigenbrode from AWS help CTOs, machine learning practitioners, business analysts, data engineers, and data scientists find a practical way to use this exciting new technology.

You'll learn the generative AI project lifecycle including use case definition, model selection, model fine-tuning, retrieval-augmented generation (RAG), reinforcement learning from human feedback (RLHF), model quantization, optimization, and deployment. You'll explore different types of models including large language models (LLMs) and multimodal models such as Stable Diffusion for generating images and video. You'll also be able to make better-informed decisions for your company regarding generative AI and learn how to build working prototypes quickly. While the focus is on AWS, this book is a great resource for learning generative AI fundamentals and applying these models to real-world applications.

• Apply generative AI to your business use cases
• Determine which generative AI models to use based on the task
• Perform prompt engineering and in-context learning
• Fine-tune generative AI models on your datasets
• Align generative AI models to human values with reinforcement learning from human feedback
• Use techniques like retrieval-augmented generation to augment your model
• Explore libraries such as LangChain and React to develop agents and actions
• Learn about multimodal models such as Stable Diffusion for image and video generation
• Get hands-on with Amazon Bedrock, the AWS generative AI managed service

如今，企業正迅速將生成式人工智慧（generative AI）整合到其產品和服務中。但對於這項技術的影響和潛力，存在著大量的炒作（和誤解）。在這本書中，來自AWS的Chris Fregly、Antje Barth和Shelbee Eigenbrode幫助CTO、機器學習從業者、業務分析師、數據工程師和數據科學家找到一種實際的方式來使用這項令人興奮的新技術。

您將學習生成式人工智慧項目的生命周期，包括用例定義、模型選擇、模型微調、檢索增強生成（RAG）、從人類反饋中進行強化學習（RLHF）、模型量化、優化和部署。您將探索不同類型的模型，包括大型語言模型（LLMs）和多模態模型，例如用於生成圖像和視頻的穩定擴散（Stable Diffusion）。您還將能夠為您的公司在生成式人工智慧方面做出更明智的決策，並學習如何快速建立工作原型。儘管重點是AWS，但這本書是學習生成式人工智慧基礎知識並將這些模型應用於實際應用的重要資源。

- 將生成式人工智慧應用於您的業務用例
- 根據任務選擇使用哪種生成式人工智慧模型
- 進行提示工程和上下文學習
- 在您的數據集上微調生成式人工智慧模型
- 通過從人類反饋中進行強化學習，將生成式人工智慧模型與人類價值觀保持一致
- 使用檢索增強生成等技術來增強您的模型
- 探索像LangChain和React這樣的庫，以開發代理和操作
- 了解用於圖像和視頻生成的多模態模型，例如穩定擴散
- 通過AWS生成式人工智慧托管服務Amazon Bedrock進行實際操作。