Webinar Overview & Outcomes
Course Description
This 12-hour webinar series takes participants from the fundamentals of Generative AI and LLMs through to production-grade LangChain applications. Early sessions build a strong foundation in LLM concepts, prompt engineering, and LangChain 1.x chains, Runnables, and LCEL. Middle sessions cover tools, agents, middleware, memory management, and guardrails. Later sessions focus on RAG systems with embeddings, vector stores, document processing, and MCP integration—providing an end-to-end path from idea to real-world LangChain deployment.
Overall Learning Outcomes
By the end of the webinar series, participants will be able to design and build complete applications using LangChain. You will be able to express applications as prompt-driven chains and tool-using agents with memory and guardrails, implement production-grade RAG pipelines backed by vector stores, and integrate external systems via MCP.
Generative AI Foundations & LangChain Basics
Module 1: Understanding Generative AI and Agents
Topics Covered
- What is Generative AI?
- What are LLMs (Large Language Models)
- Introduction to OpenAI API and ChatGPT
- Using ChatGPT for various tasks using manual prompting
- What kind of applications can be developed using these LLMs
- Understanding ReAct prompt
- Understanding Agent and how it works conceptually
- Understanding about embeddings and RAG Conceptually
- Discussion on Various cloud offerings like Azure OpenAI, Google Vertex AI and Amazon Bedrock
What You Will Learn
This module provides a comprehensive foundation in Generative AI and Large Language Models. You'll gain deep understanding of LLM capabilities and limitations, master manual prompting techniques for various use cases, and explore the ReAct (Reasoning + Acting) prompting paradigm. The module covers conceptual understanding of AI agents, their architecture, and how they work. You'll also learn the fundamentals of embeddings and RAG (Retrieval-Augmented Generation), and get insights into major cloud AI offerings including Azure OpenAI, Google Vertex AI, and Amazon Bedrock, enabling you to make informed decisions for your projects.
Hands-on Labs
- Lab 1.1: Creating a chatbot using OpenAI API and Streamlit/Gradio
Module 2: Using LangChain 1.x
Topics Covered
- Why LangChain?
- Using LangChain to make API call to OpenAI API
- Understanding various message types
- Understanding and creating a first chain
- Understanding and using Prompt Templates
- Understanding Runnables in detail
- Chaining 2 chains
- LCEL (LangChain Expression Language)
- Using Server Side tools with model
What You Will Learn
This module introduces you to LangChain 1.x, the industry-standard framework for building LLM applications. You'll understand why LangChain is essential for production-ready AI applications and learn to make API calls to OpenAI using LangChain's unified interface. The module covers different message types (System, Human, AI, Tool messages) and teaches you to create your first chain from scratch. You'll master prompt templates for consistent and effective prompting, dive deep into Runnables and their powerful capabilities, learn to combine multiple chains for complex workflows, and become proficient in LCEL (LangChain Expression Language) for declarative chain composition. Additionally, you'll learn to integrate server-side tools with LLM models.
Hands-on Labs
- Lab 2.1: Creating a chatbot using LangChain and Streamlit
- Lab 2.2: Using Runnables for chain composition and advanced workflows
Tools, Agents & Advanced Workflows
Module 3: Understanding Tools and Agents
Topics Covered
- Understanding how agents work
- Creating tools and creating agent using tools
- Understanding Middleware
- Using @wrap_model_call, @wrap_tool_call and @dynamic_prompt
- Static and Dynamic Models
- Error Handling In Tools using middleware
- Static and dynamic prompts
- Structured output using Tool Strategy and Provider Strategy
- Understanding Memory
- Memory Management Techniques like Trimming Messages, Message Summarization
- Using DatabaseToolkit and Code execution tools
- Agent response streaming
- Using Tool Runtime to access State, context, Store Commands and Stream Writer
- Mail Agent and Human In the Loop
- Implementing Guard rails
What You Will Learn
This advanced module provides deep insights into building sophisticated AI agents with LangChain. You'll gain a comprehensive understanding of agent architecture and decision-making processes, learn to create custom tools and integrate them seamlessly with agents. The module covers middleware for intercepting and modifying agent behavior, using decorators (@wrap_model_call, @wrap_tool_call, @dynamic_prompt) for enhanced control, and implementing both static and dynamic model selection. You'll master robust error handling mechanisms, create static and dynamic prompt systems, generate structured outputs using advanced strategies, and implement various memory management techniques including message trimming and summarization. The module also covers using database toolkits and code execution capabilities, streaming agent responses for better user experience, leveraging Tool Runtime for state management and context access, building mail agents and human-in-the-loop systems, and implementing guardrails for safe AI agent deployment.
Hands-on Labs
- Lab 3.1: Using Middlewares for custom functionality and error handling
- Lab 3.2: Dynamic models and Dynamic Prompts implementation
- Lab 3.3: Building a Database Agent using DatabaseToolkit
- Lab 3.4: Human In the Loop implementation with Gmail integration
- Lab 3.5: Implementing Guard rails for agent safety and compliance
- Lab 3.6: Agent response streaming for real-time interactions
- Lab 3.7: Using Tool Runtime for state management and context access
- Lab 3.8: Memory Management - Trimming messages and summarization
RAG Systems & MCP Integration
Module 4: Understanding Embeddings, Vector Store and RAG
Topics Covered
- Understanding embeddings
- What is RAG?
- Using Document Loaders, Splitters
- Indexing
- Using Chroma DB as vector store
- Understanding Similarity Search
- Retrieving using retrievers
- RAG with Agents
- RAG with Chains
What You Will Learn
This module provides comprehensive coverage of Retrieval-Augmented Generation (RAG) systems, the cornerstone of modern AI applications that need access to external knowledge. You'll master the concept of embeddings and vector representations, understand RAG architecture and its benefits, learn to load and process documents using various loaders, implement effective document splitting strategies, and create and manage vector indexes. The module covers setting up and using Chroma DB as a vector database, implementing similarity search algorithms, building and using custom retrievers, and integrating RAG with both agents and chains for enhanced capabilities and complex workflows.
Hands-on Labs
- Lab 4.1: Implementing a complete RAG system with document processing, vector store (Chroma DB), similarity search, and retrieval
- Lab 4.2: RAG with Agents - Building an intelligent agent with RAG capabilities
- Lab 4.3: RAG with Chains - Creating complex RAG workflows using chains
Module 5: Model Context Protocol (MCP)
Topics Covered
- Why MCP?
- Creating a custom MCP server
- Using MCP Servers with Claude desktop
- Stdio Client
- SSE client
- Using MCP with LangChain
What You Will Learn
This module introduces you to Model Context Protocol (MCP), a standardized protocol for connecting AI applications with external data sources and tools. You'll understand the need and benefits of MCP, learn to build custom MCP servers from scratch, integrate MCP servers with Claude Desktop, implement both Stdio-based and Server-Sent Events (SSE) MCP clients, and seamlessly integrate MCP with LangChain applications to extend your agents' capabilities with external resources.
Hands-on Labs
- Lab 5.1: Creating a custom MCP server
- Lab 5.2: Integrating MCP with Claude Desktop
- Lab 5.3: Using Stdio and SSE clients for MCP communication
- Lab 5.4: Using MCP with LangChain applications