Building LLM Powered Applications: Create intelligent apps and agents with large language models

Alto, Valentina

  • 出版商: Packt Publishing
  • 出版日期: 2024-05-22
  • 售價: $1,890
  • 貴賓價: 9.5$1,796
  • 語言: 英文
  • 頁數: 342
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 1835462316
  • ISBN-13: 9781835462317
  • 立即出貨 (庫存=1)


Get hands-on with GPT 3.5, GPT 4, LangChain, Llama 2, Falcon LLM and more, to build LLM-powered sophisticated AI applications

Key Features

  1. Embed LLMs into real-world applications
  2. Use LangChain to orchestrate LLMs and their components within applications
  3. Grasp basic and advanced techniques of prompt engineering

Book Description

Building LLM Apps delves into the fundamental concepts, cutting-edge technologies, and practical applications that LLMs offer. Ultimately paving the way for the emergence of Large Foundation Models (LFMs) that extend the boundaries of AI capabilities.

The book begins with an in-depth introduction to LLMs. We then explore various mainstream architectural frameworks, including both proprietary models (GPT 3.5/4) and open-source models (Falcon LLM), and analyze their unique strengths and differences. Moving ahead, with a focus on the Python-based, lightweight framework called LangChain. We guide readers through the process of creating intelligent agents capable of retrieving information from unstructured data and engaging with structured data using LLMs and powerful toolkits. Furthermore, the book ventures into the realm of LFMs, which transcend language modeling to encompass various AI tasks and modalities, such as vision and audio.

Whether you are a seasoned AI expert or a newcomer to the field, this book is your roadmap to unlock the full potential of LLMs and forge a new era of intelligent machines.

What you will learn

  1. Core components of LLMs' architecture, including encoder-decoders blocks, embedding and so on
  2. Get well-versed with unique features of LLMs like GPT-3.5/4, Llama 2, and Falcon LLM
  3. Use AI orchestrators like LangChain, and Streamlit as frontend
  4. Get familiar with LLMs components such as memory, prompts and tools
  5. Learn non-parametric knowledge, embeddings and vector databases
  6. Understand the implications of LFMs for AI research, and industry applications
  7. Customize your LLMs with fine tuning
  8. Learn the ethical implications of LLM-powered applications

Who this book is for

Software engineers and data scientists who want hands-on guidance for applying LLMs to build applications. The book will also appeal to technical leaders, students, and researchers interested in applied LLM topics.

We don't assume previous experience with LLM specifically. But readers should have core ML/software engineering fundamentals to understand and apply the content.


深入了解 GPT 3.5、GPT 4、LangChain、Llama 2、Falcon LLM 等技術,並建立基於 LLM 的複雜 AI 應用程式。

1. 將 LLM 嵌入實際應用程式中。
2. 使用 LangChain 在應用程式中協調 LLM 及其組件。
3. 掌握提示工程的基本和高級技術。

《Building LLM Apps》深入探討 LLM 提供的基本概念、尖端技術和實際應用。最終為 AI 能力的擴展奠定基礎,開創了大型基礎模型 (LFMs) 的出現。

本書首先深入介紹 LLM,然後探索各種主流架構框架,包括專有模型 (GPT 3.5/4) 和開源模型 (Falcon LLM),並分析它們的獨特優勢和差異。接著,重點介紹基於 Python 的輕量級框架 LangChain。我們指導讀者通過使用 LLM 和強大的工具包,創建能夠從非結構化數據中檢索信息並與結構化數據進行交互的智能代理。此外,本書還涉足 LFMs 領域,這些模型超越了語言建模,涵蓋了視覺和音頻等各種 AI 任務和模態。

無論您是經驗豐富的 AI 專家還是新手,本書都是您開啟 LLM 的全部潛力,打造智能機器新時代的路線圖。

1. LLM 架構的核心組件,包括編碼器-解碼器塊、嵌入等。
2. 熟悉 LLM 的獨特功能,如 GPT-3.5/4、Llama 2 和 Falcon LLM。
3. 使用 LangChain 和 Streamlit 等 AI 編排工具。
4. 瞭解 LLM 的組件,如記憶、提示和工具。
5. 學習非參數化知識、嵌入和向量數據庫。
6. 瞭解 LFMs 對 AI 研究和行業應用的影響。
7. 使用微調自定義您的 LLM。
8. 瞭解 LLM 應用的倫理影響。

本書適合軟體工程師和數據科學家,他們希望獲得應用 LLM 建立應用程式的實用指南。本書還適合對應用 LLM 主題感興趣的技術領導者、學生和研究人員。

我們不假設讀者具有 LLM 的先前經驗,但讀者應該具備核心機器學習/軟體工程基礎,以理解和應用內容。