Generative AI with LangChain Build Large Language Model (LLM) Apps with Python, ChatGPT, and Other LLMs
Get to grips with the LangChain framework to develop production-ready applications, including agents and personal assistants, integrating with web searches, and code execution. Purchase of the print or Kindle book includes a free PDF eBook. Key Features Learn how to leverage LLMs' capabilities...
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
Birmingham, England :
Packt Publishing Ltd
[2023]
|
| Edición: | First edition |
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009790334406719 |
Tabla de Contenidos:
- Cover
- Copyright
- Contributors
- Table of Contents
- Preface
- Chapter 1: What Is Generative AI?
- Introducing generative AI
- What are generative models?
- Why now?
- Understanding LLMs
- What is a GPT?
- Other LLMs
- Major players
- How do GPT models work?
- Pre-training
- Tokenization
- Scaling
- Conditioning
- How to try out these models
- What are text-to-image models?
- What can AI do in other domains?
- Summary
- Questions
- Chapter 2: LangChain for LLM Apps
- Going beyond stochastic parrots
- What are the limitations of LLMs?
- How can we mitigate LLM limitations?
- What is an LLM app?
- What is LangChain?
- Exploring key components of LangChain
- What are chains?
- What are agents?
- What is memory?
- What are tools?
- How does LangChain work?
- Comparing LangChain with other frameworks
- Summary
- Questions
- Chapter 3: Getting Started with LangChain
- How to set up the dependencies for this book
- pip
- Poetry
- Conda
- Docker
- Exploring API model integrations
- Fake LLM
- OpenAI
- Hugging Face
- Google Cloud Platform
- Jina AI
- Replicate
- Others
- Azure
- Anthropic
- Exploring local models
- Hugging Face Transformers
- llama.cpp
- GPT4All
- Building an application for customer service
- Summary
- Questions
- Chapter 4: Building Capable Assistants
- Mitigating hallucinations through fact-checking
- Summarizing information
- Basic prompting
- Prompt templates
- Chain of density
- Map-Reduce pipelines
- Monitoring token usage
- Extracting information from documents
- Answering questions with tools
- Information retrieval with tools
- Building a visual interface
- Exploring reasoning strategies
- Summary
- Questions
- Chapter 5: Building a Chatbot like ChatGPT
- What is a chatbot?
- Understanding retrieval and vectors
- Embeddings
- Vector storage.
- Vector indexing
- Vector libraries
- Vector databases
- Loading and retrieving in LangChain
- Document loaders
- Retrievers in LangChain
- kNN retriever
- PubMed retriever
- Custom retrievers
- Implementing a chatbot
- Document loader
- Vector storage
- Memory
- Conversation buffers
- Remembering conversation summaries
- Storing knowledge graphs
- Combining several memory mechanisms
- Long-term persistence
- Moderating responses
- Summary
- Questions
- Chapter 6: Developing Software with Generative AI
- Software development and AI
- Code LLMs
- Writing code with LLMs
- StarCoder
- StarChat
- Llama 2
- Small local model
- Automating software development
- Summary
- Questions
- Chapter 7: LLMs for Data Science
- The impact of generative models on data science
- Automated data science
- Data collection
- Visualization and EDA
- Preprocessing and feature extraction
- AutoML
- Using agents to answer data science questions
- Data exploration with LLMs
- Summary
- Questions
- Chapter 8: Customizing LLMs and Their Output
- Conditioning LLMs
- Methods for conditioning
- Reinforcement learning with human feedback
- Low-rank adaptation
- Inference-time conditioning
- Fine-tuning
- Setup for fine-tuning
- Open-source models
- Commercial models
- Prompt engineering
- Prompt techniques
- Zero-shot prompting
- Few-shot learning
- Chain-of-thought prompting
- Self-consistency
- Tree-of-thought
- Summary
- Questions
- Chapter 9: Generative AI in Production
- How to get LLM apps ready for production
- Terminology
- How to evaluate LLM apps
- Comparing two outputs
- Comparing against criteria
- String and semantic comparisons
- Running evaluations against datasets
- How to deploy LLM apps
- FastAPI web server
- Ray
- How to observe LLM apps
- Tracking responses
- Observability tools.
- LangSmith
- PromptWatch
- Summary
- Questions
- Chapter 10: The Future of Generative Models
- The current state of generative AI
- Challenges
- Trends in model development
- Big Tech vs. small enterprises
- Artificial General Intelligence
- Economic consequences
- Creative industries and advertising
- Education
- Law
- Manufacturing
- Medicine
- Military
- Societal implications
- Misinformation and cybersecurity
- Regulations and implementation challenges
- The road ahead
- Other Books You May Enjoy
- Index.
