Chip Huyen, AI Engineering

AI Engineering: Building Applications with Foundation Models

In this book, author Chip Huyen discusses AI engineering: the process of building applications with readily available foundation models.

Recent breakthroughs in AI have not only increased demand for AI products, they've also lowered the barriers to entry for those who want to build AI products. The model-as-a-service approach has transformed AI from an esoteric discipline into a powerful development tool that anyone can use. Everyone, including those with minimal or no prior AI experience, can now leverage AI models to build applications. In this book, author Chip Huyen discusses AI engineering: the process of building applications with readily available foundation models. The book starts with an overview of AI engineering, explaining how it differs from traditional ML engineering and discussing the new AI stack. The more AI is used, the more opportunities there are for catastrophic failures, and therefore, the more important evaluation becomes. This book discusses different approaches to evaluating open-ended models, including the rapidly growing AI-as-a-judge approach. AI application developers will discover how to navigate the AI landscape, including models, datasets, evaluation benchmarks, and the seemingly infinite number of use cases and application patterns. You'll learn a framework for developing an AI application, starting with simple techniques and progressing toward more sophisticated methods, and discover how to efficiently deploy these applications. Understand what AI engineering is and how it differs from traditional machine learning engineering Learn the process for developing an AI application, the challenges at each step, and approaches to address them Explore various model adaptation techniques, including prompt engineering, RAG, fine-tuning, agents, and dataset engineering, and understand how and why they work Examine the bottlenecks for latency and cost when serving foundation models and learn how to overcome them Choose the right model, dataset, evaluation benchmarks, and metrics for your needs Chip Huyen works to accelerate data analytics on GPUs at Voltron Data. Previously, she was with Snorkel AI and NVIDIA, founded an AI infrastructure startup, and taught Machine Learning Systems Design at Stanford. She's the author of the book Designing Machine Learning Systems, an Amazon bestseller in AI. AI Engineering builds upon and is complementary to Designing Machine Learning Systems (O'Reilly).

Jüngste Durchbrüche in der KI haben nicht nur die Nachfrage nach KI-Produkten erhöht, sondern auch die Einstiegshürden für diejenigen gesenkt, die KI-Produkte entwickeln möchten. Der Ansatz des Modells als Dienstleistung hat die KI von einer esoterischen Disziplin in ein leistungsstarkes Entwicklungstool verwandelt, das jeder nutzen kann. Jeder, einschliesslich derjenigen mit minimaler oder keiner vorherigen KI-Erfahrung, kann jetzt KI-Modelle nutzen, um Anwendungen zu erstellen. In diesem Buch erörtert der Autor Chip Huyen die KI-Engineering: den Prozess der Entwicklung von Anwendungen mit leicht verfügbaren Grundmodellen. Das Buch beginnt mit einem Überblick über das KI-Engineering, erklärt, wie es sich vom traditionellen Maschinenlernen-Engineering unterscheidet, und diskutiert den neuen KI-Stack. Je mehr KI eingesetzt wird, desto mehr Möglichkeiten gibt es für katastrophale Fehler, und daher wird die Bewertung umso wichtiger. Dieses Buch behandelt verschiedene Ansätze zur Bewertung offener Modelle, einschliesslich des schnell wachsenden Ansatzes der KI als Richter. Entwickler von KI-Anwendungen werden entdecken, wie sie sich im KI-Landschaft zurechtfinden, einschliesslich Modelle, Datensätze, Bewertungsbenchmarks und der scheinbar unendlichen Anzahl von Anwendungsfällen und Anwendungsmustern. Sie lernen ein Framework zur Entwicklung einer KI-Anwendung kennen, beginnend mit einfachen Techniken und fortschreitend zu komplexeren Methoden, und erfahren, wie man diese Anwendungen effizient bereitstellt. Verstehen Sie, was KI-Engineering ist und wie es sich vom traditionellen Maschinenlernen-Engineering unterscheidet. Lernen Sie den Prozess zur Entwicklung einer KI-Anwendung, die Herausforderungen in jedem Schritt und Ansätze zu deren Bewältigung. Erkunden Sie verschiedene Techniken zur Modellanpassung, einschliesslich Prompt Engineering, RAG, Feinabstimmung, Agenten und Datensatz-Engineering, und verstehen Sie, wie und warum sie funktionieren. Untersuchen Sie die Engpässe hinsichtlich Latenz und Kosten bei der Bereitstellung von Grundmodellen und lernen Sie, wie Sie diese überwinden können. Wählen Sie das richtige Modell, den richtigen Datensatz, die richtigen Bewertungsbenchmarks und Metriken für Ihre Bedürfnisse. Chip Huyen arbeitet daran, die Datenanalyse auf GPUs zu beschleunigen.

Recent breakthroughs in AI have not only increased demand for AI products, they've also lowered the barriers to entry for those who want to build AI products. The model-as-a-service approach has transformed AI from an esoteric discipline into a powerful development tool that anyone can use. Everyone, including those with minimal or no prior AI experience, can now leverage AI models to build applications. In this book, author Chip Huyen discusses AI engineering: the process of building applications with readily available foundation models. The book starts with an overview of AI engineering, explaining how it differs from traditional ML engineering and discussing the new AI stack. The more AI is used, the more opportunities there are for catastrophic failures, and therefore, the more important evaluation becomes. This book discusses different approaches to evaluating open-ended models, including the rapidly growing AI-as-a-judge approach. AI application developers will discover how to navigate the AI landscape, including models, datasets, evaluation benchmarks, and the seemingly infinite number of use cases and application patterns. You'll learn a framework for developing an AI application, starting with simple techniques and progressing toward more sophisticated methods, and discover how to efficiently deploy these applications. Understand what AI engineering is and how it differs from traditional machine learning engineering Learn the process for developing an AI application, the challenges at each step, and approaches to address them Explore various model adaptation techniques, including prompt engineering, RAG, fine-tuning, agents, and dataset engineering, and understand how and why they work Examine the bottlenecks for latency and cost when serving foundation models and learn how to overcome them Choose the right model, dataset, evaluation benchmarks, and metrics for your needs Chip Huyen works to accelerate data analytics on GPUs at Voltron Data. Previously, she was with Snorkel AI and NVIDIA, founded an AI infrastructure startup, and taught Machine Learning Systems Design at Stanford. She's the author of the book Designing Machine Learning Systems, an Amazon bestseller in AI. AI Engineering builds upon and is complementary to Designing Machine Learning Systems (O'Reilly).