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

Spis treści ebooka

• 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

pokaż cały spis treści

ukryj recenzje