Building LLM Applications using LangChain
Chapter 1: Introduction to the LangChain Framework
The Motivation for a Framework
LangChain's Core Architecture
Setting Up Your Development Environment
Your First LangChain Application
Chapter 2: Models, Prompts, and Parsers
Interfacing with LLMs and Chat Models
Managing Prompts with PromptTemplates
Implementing Few-Shot Prompting
Structuring Output with Parsers
Hands-on Practical: Building a Structured Data Extractor
Chapter 3: Constructing Chains for Sequential Operations
Fundamentals of Chains
Using the Simple LLMChain
Creating Sequential Chains
Implementing Conditional Logic with Router Chains
Hands-on Practical: A Content Generation Pipeline
Chapter 4: Memory for Conversational Applications
The Importance of State in Conversations
Buffer Memory for Short-Term Recall
Summarization Memory for Long Conversations
Using Windowed and Token-Based Memory
Adding Memory to Chains and Agents
Practice: Building a Chatbot with Memory
Chapter 5: Data Connection for Retrieval Augmented Generation (RAG)
Architecture of a RAG System
Loading Data with Document Loaders
Splitting Documents for Processing
Vector Stores and Embeddings
Fetching Data with Retrievers
Building a Question-Answering Chain
Hands-on Practical: Q&A over Your Documents
Chapter 6: Developing Autonomous Agents
Introduction to Agents and Tools
The Agent, Tool, and Toolkit Architecture
Using Built-in Tools
Creating Custom Tools
Exploring Agent Types and Executors
Hands-on Practical: A Web-Searching Agent
Hands-on Practical: A Web-Searching Agent
Was this section helpful?
- ReAct: Synergizing Reasoning and Acting in Language Models, Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao, 2023 ICLR DOI: 10.48550/arXiv.2210.03629 - Introduces the ReAct framework, which combines reasoning and acting to enable LLMs to perform complex tasks by generating verbal reasoning traces and task-specific actions. This framework directly relates to the agent loop described.
- LangChain Agents Documentation, LangChain, 2024 - Official guide to building and using agents within the LangChain framework, including concepts, components like tools and executors, and integration examples.
- Tools (Function calling), OpenAI, 2024 (OpenAI) - Provides guidance on how to enable large language models like GPT-4o to interact with external tools by defining functions the model can call, directly relevant to the agent's action generation.