{"product_id":"9781638358695","title":"Build Applications with Local AI Models on a Mac","description":"\u003cb\u003eGet the eBook free when you register your print book at Manning.\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e\u003cb\u003e\"A goldmine of technical advice, with actionable project ideas and learning resources.”\u003cbr\u003e —C. Scott Anderson, Garmin International\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e Running AI applications on local hardware unlocks architecturally guaranteed privacy, eliminates costly subscriptions and API fees, and gives you the power to tune your models to your exact needs. In \u003ci\u003eBuild Applications with Local AI Models on a Mac\u003c\/i\u003e, author \u003cb\u003eKeiji Kamigusa\u003c\/b\u003e guides you step-by-step as you build a voice-enabled chatbot that will run on any recent Mac—from a basic Mac mini to a top-of-the-line Mac Studio. As you set up your custom hardware and software stack, you’ll experience a powerful paradigm shift that turns you from a passive consumer into an AI architect.\u003cbr\u003e \u003cbr\u003e The book draws you in immediately with a hands-on project that connects three local technologies: audio capture, speech transcription, and language model inference. You’ll start by building the foundation of your chatbot, including command-line navigation and directory management, setting up Homebrew as your package manager, and downloading your first local large language model. Then, you’ll quickly review the features that make local AI on the Mac special, such as Apple Silicon’s unified memory architecture. You’ll also meet a Mac-optimized software suite that includes the Apple-optimized MLX Whisper speech recognition model that offers 100% offline privacy and an integrated voice AI pipeline that runs natively on M-series chips.\u003cbr\u003e \u003cbr\u003e As you go, you’ll explore universal concepts that apply to all AI applications—such as temperature configuration, context windows, and system prompts—and learn how they map to the specific needs of your local Mac environment. The book then guides you through expanding your assistant with Retrieval-Augmented Generation (RAG) and autonomous agents. You will store documents locally in ChromaDB to ground your AI’s responses and prevent hallucinations. You’ll also learn how to use the Python-based Streamlit framework to customize your chatbot’s behavior without writing complex callbacks or HTML.\u003cbr\u003e \u003cbr\u003e In later chapters, you’ll discover how self-hosting models on your Mac provide absolute control over your workflows while keeping your infrastructure completely private. You’ll explore the Unsloth-to-Ollama pipeline to fine-tune frontier models on your custom data and how to manage stateless LLMs by implementing explicit history tracking. Reviewer \u003cb\u003eArun Sivakumar\u003c\/b\u003e of Expedia Group noted, “The context window and token consumption are valuable details that many LLM users ignore, and concepts like how to fine tune models are highly relevant for day-to-day usage.”\u003cbr\u003e \u003cbr\u003e Spanning 18 chapters, this book provides a complete local AI roadmap. As reviewer \u003cb\u003eC. Scott Anderson\u003c\/b\u003e of Garmin International points out, this book gives you exactly what you need to see how “the benefits of open-source models can eclipse the economic realities of proprietary models.”\u003cbr\u003e \u003cbr\u003e \u003cb\u003eWhat's inside\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e • Building a fully offline, voice-enabled assistant\u003cbr\u003e • Completing data privacy with no cloud API fees\u003cbr\u003e • Maximizing Apple Silicon hardware\u003cbr\u003e • Custom Modelfiles, RAG, and local AI agent integration\u003cbr\u003e \u003cbr\u003e \u003cb\u003eAbout the reader\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e Perfect for professionals and hobbyists who want to build secure, private, and free AI applications on macOS. No prior programming or AI experience required.\u003cbr\u003e \u003cbr\u003e \u003cb\u003eAbout the author\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e \u003cb\u003eKeiji Kamigusa\u003c\/b\u003e is an authority in AI and machine learning with over 16 years of industry experience. A former CTO of a text mining company, he has created more than 50 courses and taught 59,000+ students. He holds three patents in text analytics and is the founder of AIGYM Inc., specializing in AI-driven corporate training.\u003cbr\u003e \u003cbr\u003e \u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003e Part 1\u003cbr\u003e 1 Getting started with local AI\u003cbr\u003e 2 Installing and using Homebrew\u003cbr\u003e 3 Installing and setting up Ollama\u003cbr\u003e Part 2\u003cbr\u003e 4 Downloading an LLM and having your first conversation\u003cbr\u003e 5 Setting up VS Code and your Python development environment\u003cbr\u003e 6 Creating and managing Python virtual environments\u003cbr\u003e 7 Controlling LLMs with the Ollama Python library\u003cbr\u003e 8 Building a web UI with Streamlit\u003cbr\u003e 9 Recording audio and transcribing speech with MLX Whisper\u003cbr\u003e 10 Building a voice-enabled AI chat application\u003cbr\u003e 11 Managing session state and chat history\u003cbr\u003e Part 3\u003cbr\u003e 12 Comparing and selecting LLM models\u003cbr\u003e 13 System prompts and parameter tuning\u003cbr\u003e 14 Offline LLMs and their benefits\u003cbr\u003e 15 Common errors and troubleshooting\u003cbr\u003e 16 Advancing to RAG, Web UI, and fine-tuning\u003cbr\u003e 17 The open model revolution of 2026\u003cbr\u003e 18 Where to go from here\u003cbr\u003e A Command reference\u003cbr\u003e B References and additional resources","brand":"Simon and Schuster","offers":[{"title":"eBook","offer_id":60103693664542,"sku":"9781638358695","price":50.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0741\/8436\/0222\/files\/9781638358695.jpg?v=1790944237","url":"https:\/\/shop.simonandschuster.com\/products\/9781638358695","provider":"Simon and Schuster","version":"1.0","type":"link"}