Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Gen AI - LLM RAG Two in One - LangChain + LlamaIndex
Rating: 4.1 out of 5(18 ratings)
114 students

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

Gen AI - Learn to develop RAG Applications using LangChain an LlamaIndex Frameworks using LLMs and Vector Databases
Created byManas Dasgupta
Last updated 12/2025
English

What you'll learn

  • Be able to develop your own RAG Applications using either LangChain or LlamaIndex
  • Be able to use Vector Databases effectively within your RAG Applications
  • Craft Effective Prompts for your RAG Application
  • Create Agents and Tools as parts of your RAG Applications
  • Create RAG Conversational Bots
  • Perform Tracing for your RAG Applications using LangGraph

Course content

6 sections • 28 lectures • 9h 29m total length

  • Introduction to the Course4:46
  • Introduction to Large Language Models (LLMs)32:31
  • Introduction to Prompt Engineering17:33

    Learn to craft precise, context-rich prompts for large language models, including zero-shot and few-shot approaches, and use dynamic templates with LangChain and LlamaIndex for retrieval augmented generation.

  • Prompts Advanced18:53

    Explore chain-of-thought prompting and self-consistency, and learn prompt chaining for multi-step problems. See how to test prompts in the OpenAI playground and manage context windows and tokens in Rag.

Requirements

  • Python Programming Knowledge

Description

This course leverages the power of both LangChain and LlamaIndex frameworks, along with OpenAI GPT and Google Gemini APIs, and Vector Databases like ChromaDB and Pinecone. It is designed to provide you with a comprehensive understanding of building advanced LLM RAG applications through in-depth conceptual learning and hands-on sessions. The course covers essential aspects of LLM RAG apps, exploring components from both frameworks such as Agents, Tools, Chains, Memory, QueryPipelines, Retrievers, and Query Engines in a clear and concise manner. You'll also delve into Language Embeddings and Vector Databases, enabling you to develop efficient semantic search and similarity-based RAG applications. Additionally, the course covers various Prompt Engineering techniques to enhance the efficiency of your RAG applications.

List of Projects/Hands-on included:

  1. Develop a Conversational Memory Chatbot using downloaded web data and Vector DB

  2. Create a CV Upload and Semantic CV Search App

  3. Invoice Extraction RAG App

  4. Create a Structured Data Analytics App that uses Natural Language Queries

  5. ReAct Agent: Create a Calculator App using a ReAct Agent and Tools

  6. Document Agent with Dynamic Tools: Create multiple QueryEngineTools dynamically and orchestrate queries through Agents

  7. Sequential Query Pipeline: Create Simple Sequential Query Pipelines

  8. DAG Pipeline: Develop complex DAG Pipelines

  9. Dataframe Pipeline: Develop complex Dataframe Analysis Pipelines with Pandas Output Parser and Response Synthesizer

  10. Working with SQL Databases: Develop SQL Database ingestion Bot

  11. Create a FAST API for your LangChain Application just as you would deploy in Live


    This twin-framework approach will provide you with a broader perspective on RAG development, allowing you to leverage the strengths of both LangChain and LlamaIndex in your projects.

Who this course is for:

  • Software Developers, Data Scientists, ML Engineers, DevOps Engineers, Support Engineers, Test / QA Engineers

Report abuse