LangChain Tutorial

LangChain is a framework that makes it easier to build applications using large language models (LLMs) by connecting them with data, tools and APIs. It helps developers move beyond simple text generation and create intelligent workflows.

Basics

This section introduces LangChain and explains its purpose, core features, and main modules for building LLM-powered applications.

• Introduction to LangChain
• Modules of LangChain

Prerequisites

This section covers the basic requirements for working with LangChain.

• Python Programming Basics
• APIs and Environment Setup
• Basics of Large Language Models (LLMs)
• Fundamentals of Prompt Engineering

Core Components

Here you’ll explore the essential parts of LangChain which plays a important role in building efficient, context-aware AI applications.

• Models
• Prompts
• Agents
• Memory

Working with Prompts

Prompts are the foundation of LLM interactions. In this section, you’ll learn about prompt templates and how to parse outputs effectively.

• Prompt template
• ChatPromptTemplate
• Few-Shot Prompting
• Output Parsers

Building Chains and Agents

Chains helps connect multiple steps into structured workflows, while agents make decisions to build task-oriented, multi-step AI applications.

• Sequential Chains
• LLM Chains
• Retrieval Chains
• Custom Chains
• Agents and tools
• Building a Math Application with LangChain Agents

Memory

Memory makes applications more human-like by retaining context across conversations.

• Memory in LangChain
• Conversation Buffer Memory
• Conversation Buffer Window Memory
• Conversation Summary Memory
• Vector Store Memory

Indexes and Vector Stores

This section explains how to store and retrieve information using embeddings, indexing, vector databases and RAG.

• Indexing
• Inverted Index
• Vector Stores
• Popular Vector Stores: Pinecone, FAISS, ChromaDB, Qdrant, Milvus
• Retrieval Methods: k-NN, RAG, filtering, reranking
• Scaling & Evaluation: ANN, recall/precision, latency

Integrations

LangChain supports integrations with APIs, databases and external tools.

• Integration of Langchain with Llama-Index
• RAG with LangChain
• How to use Hugging Face with LangChain

Ecosystem Tools

LangChain offers ecosystem tools like LangGraph for workflows, LangSmith for debugging and LCEL for easier development.

• LangChain Ecosystem
• What is LangGraph
• Difference Between LangChain and LangGraph
• What is LangSmith
• Debugging And Testing LLMs in LangSmith
• LangChain Expression Language (LCEL)

Practical Applications

This section focuses on real-world projects like:

• Knowledge Graphs
• Build RAG pipeline using Open Source Large Language Models
• Chatbot Webapp with LangChain
• Building a Basic PDF Summarizer LLM Application
• Building an AI application with LlamaIndex
• RAG(Retrieval-Augmented Generation) using LLama3
• Make your Documents Gen AI-ready

Advanced Topics

This part covers customizing agents, handling streaming responses, tracing and callbacks for LangChain apps.

• Customizing Chains and Agents
• Streaming Responses
• Tracing with langchain
• langchain callbacks