Advanced Generative AI with RAG Training in Chandigarh
Generative AI

Advanced Generative AI with RAG & AI Application Development

📌 Course Overview

Master advanced concepts of Generative AI by building real-world AI applications using LLMs, APIs, and RAG (Retrieval-Augmented Generation). This course focuses on hands-on development, enabling you to create intelligent chatbots, AI assistants, and data-driven applications.

Learn how to integrate tools like ChatGPT with external data sources and build production-ready AI solutions.

 

📚 Course Curriculum

From LLM APIs and prompt engineering to RAG, vector databases, LangChain, Streamlit/Flask apps, agents, deployment, and career prep.

📘 Module 1: Advanced Generative AI Foundations
  • Recap of Generative AI & LLMs
  • Limitations of LLMs (Hallucination, outdated data)
  • Introduction to APIs
  • Working with API keys
  • Making API calls using Python
📘 Module 2: Working with LLM APIs
  • Using OpenAI API
  • Sending prompts via API
  • Temperature, tokens, parameters
  • Structured output (JSON responses)
  • Prompt optimization for APIs
📘 Module 3: Prompt Engineering (Advanced)
  • Advanced prompting strategies
  • Role-based + system prompts
  • Chain-of-thought prompting
  • Prompt templates
  • Building reusable prompts
📘 Module 4: Introduction to RAG
  • What is Retrieval-Augmented Generation
  • Why RAG is needed
  • RAG architecture:
    • Data → Embeddings → Retrieval → LLM
  • Real-world use cases:
    • Chat with PDF
    • Company chatbot
📘 Module 5: Embeddings & Vector Databases
  • What are embeddings?
  • Text vectorization concepts
  • Similarity search
  • Introduction to Vector Databases:
    • FAISS
    • Pinecone
  • Storing & retrieving embeddings
📘 Module 6: Building RAG Applications
  • Loading documents (PDF, TXT, CSV)
  • Text chunking
  • Creating embeddings
  • Querying data using LLM
  • Building:
    • PDF Question Answering System
    • Knowledge-based chatbot
📘 Module 7: LangChain Framework
  • Introduction to LangChain
  • Chains & Agents
  • Memory in chatbots
  • Integrating LLM with tools
  • Building workflows
📘 Module 8: AI Application Development
  • Building AI apps using:
    • Streamlit
    • Flask (basic)
  • Creating UI for chatbot
  • Connecting backend with LLM
  • Deployment
📘 Module 9: AI Agents & Automation
  • What are AI agents
  • Task automation using LLMs
  • Multi-step reasoning systems
  • Real-world automation use cases
📘 Module 10: Capstone Projects
  • End-to-end projects combining RAG, LangChain, and deployment
📘 Module 11: Deployment & Portfolio
  • Hosting apps (Streamlit Cloud)
  • GitHub project upload
  • Portfolio building
  • Resume optimization
📘 Module 12: Career & Interview Preparation
  • Interview questions
  • Freelancing opportunities
  • Building client projects
  • Resume & LinkedIn optimization