Generative AI Application Development — RAG and Fine-Tuning
Why colleges run this
Generative AI is reshaping software; students who can build retrieval-augmented and fine-tuned applications hold one of the most sought-after current skill sets.
Course outcomes
CO1
Explain how retrieval-augmented generation grounds an LLM's answers
K2CO2
Build a vector database and retrieval step over a document set
K3CO3
Implement a retrieval-augmented application with citations
K3CO4
Evaluate a generative-AI application for relevance and hallucination
K4CO5
Deploy a generative-AI application and justify its design choices
K5Modules tap a module for its theory & lab
Hours shown are the recommended 5-day format — module time scales to the duration you pick.
01LLM foundations5 h
Theory
Capabilities, limits, the application landscape
Lab
Probe an LLM's behaviour and limits
Output
Behaviour log
02Prompt and context engineering5 h
Theory
Patterns, structured output, guardrails
Lab
Engineer prompts for reliable output
Output
Prompt library
03Embeddings and vector databases5 h
Theory
Chunking, indexing, similarity search
Lab
Index a corpus in a vector database
Output
Vector index
04Retrieval-augmented generation5 h
Theory
Grounding answers, citations
Lab
Build a RAG pipeline with citations
Output
RAG pipeline
05Evaluation5 h
Theory
Relevance, faithfulness, hallucination
Lab
Evaluate the RAG application
Output
Evaluation report
06Fine-tuning5 h
Theory
When and how to fine-tune, dataset preparation
Lab
Prepare data and fine-tune a model
Output
Fine-tuned model
07Orchestration5 h
Theory
Chaining, tools, agents
Lab
Orchestrate a multi-step flow
Output
Orchestrated flow
08Capstone5 h
Theory
A deployed GenAI application with evaluation
Lab
Ship and evaluate the capstone
Output
Deployed GenAI application
Every participant receives
Certificate of completion Course material LMS access Interview question bank Mock interview & viva practice Optional nasscom NSQF assessment