LangChain in Your Pocket LangChain Essentials
"Learn about LangChain and LLMs with ""LangChain in your Pocket,"" a comprehensive guide to leveraging this innovative framework for building language-based applications. Key Features Step-by-step code explanations with expected outputs for each solution Practical examples a...
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
La Vergne :
Mehul Gupta
[2024]
|
| Edición: | First edition |
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009820529906719 |
Tabla de Contenidos:
- Intro
- Copyright
- Preface
- Table Of Contents
- Chapter 1: Introduction
- 1.1 What are LLMs?
- 1.2 Different LLM families
- 1.3 What is LangChain used for?
- 1.4 Why LangChain?
- 1.5 Book Overview
- (Untitled)
- (Untitled)
- Chapter 2: Hello World
- 2.1 Setting up LangChain
- 2.2 Name Generator
- 2.3 Text Pre-processing
- 2.4 Storyteller
- 2.5 LangChain using Local LLMs
- (Untitled)
- (Untitled)
- Chapter 3: Different LangChain Modules
- Chapter 4: Models and Prompts
- 4.1 Models
- 4.1.1 LLM
- 4.1.2 ChatModel
- 4.2 Prompts
- 4.2.1 PromptTemplate
- 4.2.2 ChatPromptTemplate
- Chapter 5: Chains
- 5.1 LLMChain
- 5.2 Auto-SQL Chain
- 5.3 MathsChain
- 5.4 DALL-E using LLMChain
- 5.5 Custom Chains using LCEL
- 5.6 Types of Chains
- (Untitled)
- (Untitled)
- Chapter 6: Agents
- 6.1 How are Agents different from Chains?
- 6.2 Building Agents using LangChain
- 6.3 Types of Agents
- 6.4 Custom Tools for Agents
- (Untitled)
- Chapter 7: OutputParsers and Memory
- 7.1 OutputParsers
- 7.1.1 CommaSeparatedListOutputParser
- 7.1.2 Custom OutputParser
- 7.1.3 Magic Output Fixer
- 7.2 Memory
- 7.2.1 ConversationalBufferMemory
- 7.2.2 ConversationSummaryMemory
- Chapter 8: Callbacks
- 8.1 What are Callbacks?
- 8.2 StdOutputCallbackHandler
- 8.3 FileHandler
- 8.4 Custom Callbacks
- Chapter 9: RAG Framework and Vector Databases
- 9.1 What is RAG?
- 9.2 Different components of RAG
- 9.3 RAG using LangChain
- 9.4 Multi-document RAG
- 9.5 Recommendation System using RAG
- 9.6 Vector Databases
- Chapter 10: LangChain for NLP problems
- 10.1 Summarization
- 10.2 Text Tagging and Classification
- 10.3 Named Entity Recognition
- 10.4 Text Embeddings
- 10.5 Few-Shot Classification
- 10.5.1 What is Few-Shot Learning?
- 10.5.2 Multi-Classification
- 10.5.3 Example Selection.
- 10.6 POS Tagging, Segmentation and more
- Chapter 11: Handling LLM Hallucinations
- 11.1 What are Hallucinations?
- 11.2 Why do LLMs Hallucinate?
- 11.3 LLMCheckerChain
- 11.4 LLMSummarizationChain
- 11.5 Avoiding Hallucinations using RAG
- (Untitled)
- (Untitled)
- Chapter 12: Evaluating LLMs
- 12.1 String Evaluators
- 12.1.1 Criteria Evaluators
- 12.1.2 Custom Evaluators
- 12.2 Comparison Evaluators
- 12.3 Trajectory Evaluators
- (Untitled)
- (Untitled)
- Chapter 13: Advanced Prompt Engineering
- 13.1 Chain of Thoughts
- 13.1.1 Think Step by Step
- 13.1.2 Few-Shot Prompting
- 13.2 ReAct
- 13.3 Tree of Thoughts
- 13.4 Other Prompt Engineering Techniques
- Chapter 14: Autonomous AI agents
- 14.1 What is AGI?
- 14.2 AutoGPT
- 14.3 BabyAGI
- 14.4 HuggingGPT
- Chapter 15: LangSmith and LangServe
- 15.1 LangSmith
- 15.2 LangServe
- Chapter 16: Additional Features
- 16.1 Fallbacks
- 16.1.1 Fallback for LLMs
- 16.1.2 Fallback for Chains
- 16.2 Safety
- 16.2.1 OpenAIModerationChain
- 16.2.2 ConstitutionalChain
- 16.3 Model Laboratory
- 16.4 Debugging and Verbose
- Endnotes
- About the Author.
