BTech / BCA Track6 Weeks CohortTopic-Linked Attendance Enabled
Generative AI (GenAI) — Architectures & RAG
Learn modern Generative AI, Large Language Models (LLMs), prompt engineering, structured JSON outputs, OpenAI/Gemini API integration, and Retrieval-Augmented Generation (RAG) with Vector Databases.
Key Skills You Will Master:
LLMsPrompt EngineeringGemini & OpenAI APIsRAG ArchitectureChromaDB / PineconeAI Agents
Lead Instructor
Vikramaditya Iyer
Ex-Tech Lead & STEM Mentor
Total Program Fee (Full Cohort + Materials)
₹3,499₹4,999Save 30%
Choose Your CohortLive Interactive
Next cohort starting next weekend • 5:00 PM IST
10 Live Hybrid Interactive Sessions
10 Granular Tracked Topics
Downloadable datasets, cheatsheets & spreadsheets
Verifiable Certificate upon 85%+ topic completion
Syllabus Breakdown
Course Structure & Tracked Topics
Click on any module to view live sessions and the exact list of topics tested & tracked for attendance.
Session 1 • 90 Minutes Live
Session 1: Transformers & LLM Foundations
Granular Tracked Topics (1):
Self-Attention, Tokens, Temperature, Top-p Parameters
Session 2 • 90 Minutes Live
Session 2: Systematic Prompt Engineering
Granular Tracked Topics (1):
Zero/Few-Shot Prompting, Chain-of-Thought, System Prompts
Session 3 • 90 Minutes Live
Session 3: Structured JSON & Function Calling
Granular Tracked Topics (1):
JSON Schema Enforcement & LLM Tool/Function Calling
Beginner Milestone: Automated Outreach & Proposal Generator
A prompt script that parses client profiles and outputs structured JSON sales sequences.
Deliverable: Prompt engineering notebook with deterministic JSON schemas.
Session 1 • 90 Minutes Live
Session 4: LLM API Integration (Gemini & OpenAI)
Granular Tracked Topics (1):
API Keys, Client SDKs, Streaming Responses, Token Cost Management
Session 2 • 90 Minutes Live
Session 5: Embeddings & Vector Databases
Granular Tracked Topics (1):
Semantic Embeddings, Cosine Similarity, ChromaDB Setup
Session 3 • 90 Minutes Live
Session 6: Retrieval-Augmented Generation (RAG)
Granular Tracked Topics (1):
Document Chunking, Embedding Ingestion, Context Injection
Intermediate Milestone: HR Policy & PDF RAG Knowledge Base
A RAG system indexing PDF employee handbooks allowing natural language queries with cited page numbers.
Deliverable: Working RAG pipeline querying ChromaDB with zero hallucination.
Session 1 • 90 Minutes Live
Session 7: AI Agents & ReAct Tool Execution
Granular Tracked Topics (1):
ReAct Agent Loop, Web Search & Calculator Tool Calling
Session 2 • 90 Minutes Live
Session 8: Multimodal LLMs & Vision
Granular Tracked Topics (1):
Multimodal Vision Prompts & Image Understanding
Session 3 • 90 Minutes Live
Session 9: Production Guardrails & Safety
Granular Tracked Topics (1):
Hallucination Mitigation, Prompt Injections & Guardrails
Session 4 • 90 Minutes Live
Session 10: Capstone RAG Application Showcase
Granular Tracked Topics (1):
Live Multimodal RAG Web App Defense
Graduation Capstone Portfolio
Enterprise Knowledge Base & Multimodal RAG AI Assistant
Build a production GenAI web app with PDF document ingestion, ChromaDB vector search, streaming LLM responses with citations, and agentic fallback.
Deliverable:
Live Web App + Full Vector RAG Pipeline Codebase
What You Will Be Able To Do
Master prompt engineering patterns (Few-Shot, Chain-of-Thought, Structured Output)
Programmatically integrate Google Gemini and OpenAI LLM APIs
Build end-to-end Retrieval-Augmented Generation (RAG) pipelines over custom documents
Deploy autonomous AI Agents with tool calling and vector memory
Prerequisites
Python basics recommended.