Hugging Face in Action

Everything you need to know about using the tools, libraries, and models at Hugging Face--from transformers, to RAG, LangChain, and Gradio.

Hugging Face in Action reveals how to get the absolute best out of everything Hugging Face, from accessing state-of-the-art models to building intuitive frontends for AI apps.

With Hugging Face in Action you’ll learn:

- Utilizing Hugging Face Transformers and Pipelines for NLP tasks
- Applying Hugging Face techniques for Computer Vision projects
- Manipulating Hugging Face Datasets for efficient data handling
- Training Machine Learning models with AutoTrain functionality
- Implementing AI agents for autonomous task execution
- Developing LLM-based applications using LangChain and LlamaIndex
- Constructing LangChain applications visually with LangFlow
- Creating web-based user interfaces using Gradio
- Building locally running LLM-based applications with GPT4ALL
- Querying local data using Large Language Models

Want a cutting edge transformer library? Hugging Face’s open source offering is best in class. Need somewhere to host your models? Hugging Face Spaces has you covered. Do your users need an intuitive frontend for your AI app? Hugging Face’s Gradio library makes it easy to build UI using the Python skills you already have. In Hugging Face in Action you’ll learn how to take full advantage of all of Hugging Face’s amazing features to quickly and reliably prototype and productionize AI applications.

About the technology

Hugging Face is an incredible open-source ecosystem for AI engineers and data scientists, providing hundreds of pre-trained models, datasets, tools, and libraries. It’s also a central hub for collaborating on leading edge AI research. Hugging Face is a massive platform, and this book will help you take full advantage of all it has to offer.

About the book

Hugging Face in Action teaches you how to build end-to-end AI systems using resources from the Hugging Face community. In it, you’ll create multiple projects, including an object detection model, a RAG Q&A application, an LLM-powered chatbot, and more. You’ll appreciate the clear, accessible explanations, along with thoughtful introductions to key technologies like LangChain, LlamaIndex, and Gradio.
What’s inside

- How to navigate the huge Hugging Face library of models and tools
- How to run LLMs locally using GPT4ALL
- How to create web-based user interfaces using Gradio
- How to improve models using Hugging Face datasets

About the reader

For Python programmers familiar with NumPy and Pandas. No AI experience required.

About the author

Wei-Meng Lee is a technologist and founder of Developer Learning Solutions.

Table of Contents

1 Introducing Hugging Face
2 Getting started
3 Using Hugging Face transformers and pipelines for NLP tasks
4 Using Hugging Face for computer vision tasks
5 Exploring, tokenizing, and visualizing Hugging Face datasets
6 Fine-tuning pretrained models and working with multimodal models
7 Creating LLM-based applications using LangChain and LlamaIndex
8 Building LangChain applications visually using Langflow
9 Programming agents
10 Building a web-based UI using Gradio
11 Building locally running LLM-based applications using GPT4All
12 Using LLMs to query your local data
13 Bridging LLMs to the real world with the Model Context Protocol

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

Wei-Meng Lee is a technologist and founder of Developer Learning Solutions, a company specializing in helping companies adopt the latest IT technologies. Wei-Meng provides consultancy services to companies on adopting blockchain and AI solutions for their businesses.