top of page
Generative AI Bootcamp
Generative AI Bootcamp
 
Course Description
This course is your hands-on gateway to building Generative AI applications using LangChain, RAG, and CrewAI. You’ll start by setting up your environment—installing Anaconda, Jupyter Notebook, VS Code, CUDA Toolkit, cuDNN, and PyTorch with GPU support. From there, you’ll cover Python fundamentals before diving into the core concepts of AI and Generative AI.
 
You’ll gain practical skills in:
  • LangChain workflows: chaining components, loading documents, applying memory, and building RAG pipelines.
  • Prompt engineering: designing effective prompts for real-world use cases.
  • Multi-agent frameworks: leveraging CrewAI to build collaborative AI agents.
  • Vector databases & chunking methods: managing knowledge efficiently in RAG systems.
  • Model integration: using Hugging Face and open-source LLMs to power applications.
By the end, you’ll not only understand how Generative AI systems work, but also be able to build and deploy your own AI-powered applications with confidence.
 
Who This Course Is For
  • Developers building practical Generative AI applications with LangChain and RAG.
  • Programmers eager to design multi-agent frameworks.
  • AI engineers and data scientists looking to expand their expertise in next-generation AI tools.
 
What You’ll Learn
  • Build Generative AI applications using LangChain, mastering its key components.
  • Design multi-agent systems with CrewAI and LangChain tools, exploring their core elements in depth.
  • Create Retrieval-Augmented Generation (RAG) pipelines: input preparation, text chunking, embeddings, vector stores, similarity search, and pipeline integration.
  • Apply prompt engineering techniques with hands-on practice, including Basic, Role Task Context, Few-Shot, Chain of Thought, and Constrained Output Prompting.
  • Implement LangChain chains such as Single, Sequential, Math, RAG, Router, LLM Router, SQL Chains, and more.
  • Work with document loaders like CSVLoader, HTMLLoader, PDFLoader, and others.
  • Explore Hugging Face models and integrate them into practical Generative AI applications.
  • Master text chunking methods for RAG systems: Character, Recursive Character, Markdown Header, and Token Splitters.
  • Gain expertise in vector databases for RAG, including Pinecone, Chroma, Weaviate, Milvus, and FAISS.
  • Understand the fundamentals of AI, Machine Learning, Deep Learning, and Generative AI, along with their history and applications.
  • Learn how transformers work—attention mechanisms, encoding, and decoding.
  • Explore foundation models: their evolution, types, applications, and leading examples.
  • Compare language model performance, review top open-source LLMs, and learn how to select the right foundation model.
  • Embrace responsible AI practices, focusing on fairness, ethics, and bias mitigation.
  • Implement memory types in LLMs, including ConversationBufferMemory, Buffer Window, and ConversationSummaryMemory.
 
Requirements
  • Familiarity with Python is preferred (basics covered in the course).
  • Access to a computer with a stable internet connection.
  • Accounts with OpenAI, Claude (Anthropic), or open-source models.
  • Basic knowledge of code editors like Jupyter Notebook or VS Code.
 
 

Generative AI Bootcamp

    bottom of page