Gen AI - LLM RAG Two in One - LangChain + LlamaIndex

What you will be able to do

• Develop custom RAG applications with LangChain or LlamaIndex
• Use vector databases (ChromaDB, Pinecone) inside RAG pipelines
• Design prompts tailored to RAG systems
• Build agents and custom tools for RAG workflows
• Build conversational chatbots with memory
• Trace applications with LangGraph and deploy them with FastAPI

Curriculum

1. 01IntroductionLLM and prompt engineering foundations.

   • Introduction to Large Language Models (LLMs)
   • Introduction to Prompt Engineering
   • Prompts Advanced
2. 02Starting with LangChainEnvironment setup and a first program with Google Gemini.

   • Introduction to LangChain
   • LangChain Environment Setup
   • Using Google Gemini LLM
   • Our First LangChain Program
3. 03Learn LangChain through ProjectsFive RAG projects on structured and unstructured data.

   • Working with SQL Data - RAG Application
   • Create a CV Upload and Search Application
   • Create an Invoice Extract RAG Application
   • Create a Conversational Chatbot for HR Policy Queries
   • Analysis of Structured Data using Natural Language
4. 04Getting Started with LlamaIndexSetup and a first LlamaIndex program.

   • Introduction to LlamaIndex
   • LlamaIndex setup
   • Our First LlamaIndex Program
5. 05Learn LlamaIndex through ProjectsVector databases, query pipelines, agents and tools.

   • RAG App using Chroma DB Vector Database
   • LlamaIndex RAG with SQL Database
   • LlamaIndex Query Pipelines
   • LlamaIndex Complex DAG Pipeline
   • Working with Agents and Tools
   • Create a Calculator RAG App using ReAct Agents
   • Create a Document Agent with Dynamically built Tools
   • Create a Code Checker RAG App
6. 06Creating a FastAPI for production deploymentServe a LangChain application as an API.

   • Creating a FastAPI for production deployment of your LangChain Application

Prerequisites

• Python programming knowledge

Frequently asked questions