Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Build AI Agents & RAG Apps with LangChain & CrewAI
Rating: 4.5 out of 5(33 ratings)
562 students

Build AI Agents & RAG Apps with LangChain & CrewAI

Build real-world GenAI apps with RAG, LangChain, CrewAI, Hugging Face, Prompt Engineering and Python
Created byTech With Mala
Last updated 3/2026
English

What you'll learn

  • Build real-world Generative AI applications using LangChain and understand its core components
  • Design and develop multi-agent AI systems using CrewAI with hands-on projects
  • Create end-to-end RAG (Retrieval-Augmented Generation) pipelines including chunking, embeddings, vector stores, and retrieval
  • Master prompt engineering techniques: Basic, Role–Task–Context, Few-shot, Chain-of-Thought, and Constrained Outputs
  • Implement a wide range of LangChain chains: Single, Sequential, Router, RAG, Math, SQL, and more
  • Work with document loaders (CSV, HTML, PDF) to build AI systems using real-world data
  • Use Hugging Face models to build applications like summarization, translation, embeddings, and vision tasks
  • Apply different text chunking strategies: Character, Recursive, Markdown Header, and Token-based methods
  • Explore vector databases for RAG systems: Pinecone, FAISS, Chroma, Weaviate, and Milvus
  • Understand core concepts of AI, Machine Learning, Deep Learning, and Generative AI
  • Learn how Transformers and Attention mechanisms work (Encoder–Decoder architecture)
  • Gain a solid understanding of Foundation Models, their applications, types, and real-world use cases
  • Evaluate LLM performance, compare top open-source models, and choose the right model for your use case
  • Learn Responsible AI practices and how to identify and mitigate bias in AI systems
  • Implement memory in LLM applications using Conversation Buffer, Window Memory, and Summary Memory

Course content

14 sections • 72 lectures • 14h 3m total length

  • Course Overview8:19

Requirements

  • We cover Python basics but prefer to have familiarity with the Python programming language.
  • Access to a computer with good internet connection.
  • Have access to OpenAI, Claude Anthropic, or you can use open source models
  • Basic understanding on using different code editors - Jupyter notebook, VScode, etc.

Description

Build real-world Generative AI applications using the latest tools like LangChain, RAG, AI Agents (CrewAI), and Hugging Face—all in one complete, hands-on course.

This course takes you from absolute setup to advanced AI systems, helping you understand not just how things work, but how to build production-ready AI applications.

Get Started from Scratch

Set up your development environment with ease:

  • Install Anaconda, Jupyter Notebook, and VS Code

  • Master Jupyter Notebook Markdown for clean workflows

  • Enable GPU with CUDA, cuDNN, and PyTorch

Learn Python for AI (Beginner Friendly)

Build a strong foundation in Python:

  • Variables, data types, and type conversion

  • Control statements, loops, and functions

  • Core data structures: lists, tuples, sets, dictionaries, strings

Understand AI, ML & Generative AI

  • AI, Machine Learning, Deep Learning & Generative AI explained

  • Evolution and history of AI

  • Deep dive into Transformers & Attention Mechanism (Encoder–Decoder)

Master Foundation Models & Responsible AI

  • What are Foundation Models and how they work

  • Applications, types, and real-world examples

  • Compare top open-source LLMs and choose the right model

  • Learn Responsible AI practices and bias mitigation

Build LLM Apps with LangChain

  • Chains, Agents, and Memory explained

  • Build powerful LLM-driven applications step by step

Master RAG (Retrieval-Augmented Generation)

  • End-to-end RAG pipeline:
    Input → Chunking → Embeddings → Vector DB → Retrieval → Response

  • Build a complete Question-Answering system

  • Work with vector databases:
    Pinecone, FAISS, Chroma, Weaviate, Milvus

Advanced Text Chunking Strategies

Learn and implement multiple chunking techniques:

  • Character & Recursive Character Splitters

  • Markdown Header Splitter

  • Token-based Chunking

  • Best practices for optimal RAG performance

Prompt Engineering Like a Pro

  • Create and use OpenAI APIs

  • Master prompting techniques:

    • Basic prompts

    • Role–Task–Context

    • Few-shot prompting

    • Chain-of-Thought

    • Constrained outputs

Work with Real Data

  • Use document loaders: CSV, HTML, PDF

  • Feed real-world data into your AI systems

Add Memory to LLMs

  • Conversation Buffer Memory

  • Window Memory

  • Summary Memory

  • Build AI that remembers context

Master LangChain Chains

  • Single, Sequential & Router Chains

  • Math Chain, SQL Chain, RAG Chain

  • Build intelligent workflows with LLMs

Build Multi-Agent AI Systems (CrewAI)

  • Understand Agentic AI frameworks

  • Build real-world systems:

    • Web scraping agents

    • Email automation agents

    • Financial analysis agents

  • Integrate LangChain tools with CrewAI

Build Apps with Hugging Face

  • Use pretrained models for:

    • Text summarization

    • Translation

    • Sentence embeddings

    • Vision-based tasks (Image Q&A)

By the End of This Course, You Will:

  • Build real-world GenAI applications from scratch

  • Master RAG, LangChain, and AI Agents

  • Work with industry tools used in AI engineering roles

  • Be ready to create your own AI-powered products

Who this course is for:

  • Developers interested in building Generative AI applications using LangChain, RAG.
  • Programmers interested in building multi agentic frameworks.
  • AI engineers and data scientists.

Report abuse