Developing Apps with GPT-4 and ChatGPT. 2nd Edition - Helion

ebook

Autor: Olivier Caelen, Marie-Alice Blete
ISBN: 9781098168063
stron: 272, Format: ebook
Data wydania: 2024-07-10
Księgarnia: Helion

Cena książki: 144,18 zł (poprzednio: 208,96 zł)
Oszczędzasz: 31% (-64,78 zł)

Osoby, które kupiły tę książkę, wybierały także »

This book provides an ideal guide for Python developers who want to learn how to build applications with large language models. Authors Olivier Caelen and Marie-Alice Blete cover the main features and benefits of GPT-4 and GPT-3.5 models and explain how they work. You'll also get a step-by-step guide for developing applications using the OpenAI Python library, including text generation, Q&A, and smart assistants.

Written in clear and concise language, Developing Apps with GPT-4 and ChatGPT includes easy-to-follow examples to help you understand and apply the concepts to your projects. Python code examples are available in a GitHub repository, and the book includes a glossary of key terms. Ready to harness the power of large language models in your applications? This book is a must.

You'll learn:

Fundamentals and benefits of GPT-4 and GPT-3.5 models, including the main features and how they work
How to integrate these models into Python-based applications, leveraging natural language processing capabilities and overcoming specific LLM-related challenges
Examples of applications demonstrating the OpenAI API in Python for tasks including text generation, question answering, content summarization, classification, and more
Advanced LLM topics such as prompt engineering, fine-tuning models for specific tasks, RAG, plug-ins, LangChain, LlamaIndex, GPTs, and assistants

Olivier Caelen is a machine learning researcher at Worldline and teaches machine learning courses at the University of Brussels.

Marie-Alice Blete, a software architect and data engineer in Worldline's R&D department, is interested in performance and latency issues associated with AI solutions.

Osoby które kupowały "Developing Apps with GPT-4 and ChatGPT. 2nd Edition", wybierały także:

Cisco CCNA 200-301. Kurs video. Administrowanie bezpieczeństwem sieci. Część 3 665,00 zł, (39,90 zł -94%)
Cisco CCNA 200-301. Kurs video. Administrowanie urządzeniami Cisco. Część 2 665,00 zł, (39,90 zł -94%)
Cisco CCNA 200-301. Kurs video. Podstawy sieci komputerowych i konfiguracji. Część 1 665,00 zł, (39,90 zł -94%)
Impact of P2P and Free Distribution on Book Sales 427,14 zł, (29,90 zł -93%)
Cisco CCNP Enterprise 350-401 ENCOR. Kurs video. Programowanie i automatyzacja sieci 443,33 zł, (39,90 zł -91%)

Spis treści

Developing Apps with GPT-4 and ChatGPT. 2nd Edition eBook -- spis treści

Preface
- Conventions Used in This Book
- Using Code Examples
- OReilly Online Learning
- How to Contact Us
- Acknowledgments
1. GPT-4 and ChatGPT Essentials
- Introducing Large Language Models
  - Exploring the Foundations of Language Models and NLP
  - Understanding the Transformer Architecture and Its Role in LLMs
  - Demystifying the Tokenization and Prediction Steps in GPT Models
  - Integrating Vision into an LLM
- A Brief History: From GPT-1 to GPT-4
  - GPT-1
  - GPT-2
  - GPT-3
  - From GPT-3 to InstructGPT
  - GPT-3.5, ChatGPT, Codex
  - GPT-4
  - The Evolution of AI Toward Multimodality
    - Image generation with DALL-E
    - Voice recognition and synthesis
    - Video generation with Sora
- LLM Use Cases and Example Products
  - Be My Eyes
  - Morgan Stanley
  - Khan Academy
  - Duolingo
  - Yabble
  - Waymark
  - Inworld AI
- Beware of AI Hallucinations: Limitations and Considerations
- Unlocking GPT Potential with Advanced Features
- Summary
2. A Deep Dive into the OpenAI API
- Essential Concepts
- Models Available in the OpenAI API
  - GPT Base
  - InstructGPT (Legacy)
  - GPT-3.5
  - GPT-4
- Trying GPT Models with the OpenAI Playground
- Getting Started: The OpenAI Python Library
  - OpenAI Access and API Key
  - Hello World Example
- Using Chat Completion Models
  - Input Options for the Chat Completion Endpoint
    - Required input parameters
    - Length of conversations and tokens
    - Additional optional parameters
  - Playing with temperature and top_p
  - Output Result Format for the Chat Completion Endpoint
  - Vision
  - Requiring a JSON Output
    - JSON output format
    - Tools and functions
- Using Other Text Completion Models
  - Input Options for the Text Completion Endpoint
    - Main input parameters
    - Length of prompts and tokens
    - Additional optional parameters
  - Output Result Format for the Text Completion Endpoint
- Considerations
  - Pricing and Token Limitations
  - Security and Privacy: Caution!
- Other OpenAI APIs and Functionalities
  - Embeddings
  - Moderation
  - Text-to-Speech
  - Speech-to-Text
  - Images API
    - Image generations
    - Image edits
    - Image variations
- Summary (and Cheat Sheet)
3. Navigating LLM-Powered Applications: Capabilities and Challenges
- App Development Overview
  - API Key Management
    - The user provides the API key
    - You provide the API key
  - Security and Data Privacy
- Software Architecture Design Principles
- Integrating LLM Capabilities into Your Projects
  - Conversational Capabilities
  - Language Processing Capabilities
  - Human-Computer Interaction Capabilities
  - Combining Capabilities
- Example Projects
  - Project 1: Building a News Generator SolutionLanguage Processing
  - Project 2: Summarizing YouTube VideosLanguage Processing
  - Project 3: Creating an Expert for Zelda BOTWLanguage Processing and Conversations
    - Redis
    - Information retrieval service
    - Intent service
    - Response service
    - Putting it all together
  - Project 4: Having a Personal AssistantHuman-Computer Interface
    - Speech-to-text with Whisper
    - Assistant with GPT-3.5 Turbo
    - UI with Gradio
    - Demonstration
  - Project 5: Organizing DocumentsLanguage Processing
  - Project 6: Analyzing SentimentsLanguage Processing
    - Evaluation of classification model
- Cost Management
- LLM-Powered App Vulnerabilities
  - Analyzing Inputs and Outputs
  - The Inevitability of Prompt Injection
- Working with an External API
  - Handling Errors and Unexpected Latency Issues
  - Rate Limits
  - Improving Responsiveness and User Experience
    - Streaming
    - Asynchronous programming
    - Other design strategies
- Summary
4. Advanced LLM Integration Strategies with OpenAI
- Prompt Engineering
  - Designing Effective Prompts with Roles, Contexts, and Tasks
    - The context
    - The task
    - The role
  - Thinking Step by Step
  - Implementing Few-Shot Learning
  - Iterative Refinement with User Feedback
  - Improving Prompt Effectiveness
    - Instruct the model to ask more questions
    - Format the output
    - Repeat the instructions
    - Use negative prompts
    - Add length constraints
    - Prompt chaining
    - Shadow prompting
- Fine-Tuning
  - Getting Started
    - Adapting GPT models for domain-specific needs
    - Fine-tuning versus few-shot learning
  - Fine-Tuning with the OpenAI API
    - Preparing your data
    - Making your data available
    - Creating a fine-tuned model
    - Listing fine-tuning jobs
    - Canceling a fine-tuning job
    - Getting status updates for a fine-tuning job
    - Getting info about a fine-tuning job
  - Fine-Tuning with the Web Interface of OpenAI
  - Fine-Tuning Applications
    - Legal document analysis
    - Automated code review
    - Financial document summarization
    - Technical document translation
    - News article generation for niche topics
  - Generating and Fine-Tuning Synthetic Data for an Email Marketing Campaign
    - Creating a synthetic dataset
    - Fine-tuning a model with the synthetic dataset
    - Evaluating the fine-tuned model
    - Using the fine-tuned model for text completion
  - Cost of Fine-Tuning
- RAG
  - Naive RAG
  - Advanced RAG
    - Preprocess the users query
    - Preprocess the knowledge base
    - Improving search
    - Postprocessing
  - RAG Limitations
- Choosing Between Strategies
  - Strategy Comparison
  - Evaluations
- From a Standard Application to an LLM-Powered Solution
  - Prompt Sensitivity
  - Nondeterminism
  - Hallucinations
- Summary
5. Advancing LLM Capabilities with Frameworks, Plug-Ins, and More
- The LangChain Framework
  - LangChain Libraries
  - Dynamic Prompts
  - Agents and Tools
  - Memory
  - Embeddings
- The LlamaIndex Framework
  - Demonstration: RAG in 10 Lines of Code
  - LlamaIndex Principles
  - Customization
- GPT-4 Plug-Ins
  - Overview
  - The API
  - The Plug-In Manifest
  - The OpenAPI Specification
  - Descriptions
- GPTs
- The Assistant API
  - Creating an Assistant API
  - Managing a Conversation with Your Assistant API
  - Function Calling
  - The Assistants on the OpenAI Web Platform
    - Testing an assistant on the OpenAI website
    - Creating an assistant on the OpenAI website
- Summary
6. Putting It All Together
- Key Takeaways
- Putting It All Together: The Assistant Use Case
  - Step 1: Ideation
  - Step 2: Defining the Requirements
  - Step 3: Building a Prototype
  - Step 4: Improving, Iterating
  - Step 5: Making the Solution Robust
- Lessons Learned
Glossary of Key Terms
A. Tools, Libraries, and Frameworks
Index