Generative AI

Build, evaluate and ship applications powered by large language models.

  • Duration50 hoursTraining hours, including guided labs
  • Modules10Each module ends with hands-on practice
  • ProjectsLabs + capstoneBuilt, reviewed and demonstrated
  • LevelBeginner to intermediate

Course overview

50 hours, 10 modules, one capstone

A 50-hour course that goes from how large language models work to shipping real applications with them. Learners practise prompt engineering with hosted and open models, build apps with LangChain and Streamlit, and create retrieval-augmented (RAG) systems over their own documents. They finish by evaluating quality, knowing when to fine-tune and applying responsible-AI practices.

Learning objectives

  • Explain how LLMs work, including tokens, transformers, context windows and hallucination.
  • Write reliable prompts and get structured output from hosted and open models.
  • Build LLM applications with LangChain and give them a Streamlit interface.
  • Build, evaluate and improve a retrieval-augmented generation (RAG) system.
  • Decide between prompting, RAG and fine-tuning, and apply responsible-AI practices.

Who it is for

Students, fresh graduates, developers and analysts who want to build AI features into products.

Prerequisites
Working Python: functions, lists, dictionaries and pip. No machine-learning background is required.
Level
Beginner to intermediate
Status
Coming soon. Join the waitlist to hear first when registrations open.
Duration
50 hours of training, including guided labs
Join the waitlist

What you will learn

Skills covered in this course

No prior AI background needed; working Python is enough.

LLM foundations

TokensTransformersContext windowsModel choice

Prompt engineering

Few-shotChain of thoughtStructured output

LLM applications

LangChainOutput parsersMemoryStreamlit

RAG and evaluation

EmbeddingsVector databasesRAGRAGASLoRA

Syllabus

Module-by-module curriculum

10 modules, 50 hours in total. Every module ends with hands-on practice.

01
Module 1

AI and Generative AI foundations

3 hrs
  1. 1.1The landscapeAI vs machine learning vs deep learning · what makes AI generative · real-world use cases
  2. 1.2Model familiesfoundation models · open-source vs closed-source LLMs · text, image, audio and multimodal models
02
Module 2

How large language models work

4 hrs
  1. 2.1Inside an LLMtokens and tokenisation · embeddings · transformers and attention
  2. 2.2Training and behaviourpre-training vs instruction tuning · context windows · temperature and top-p · why models hallucinate
03
Module 3

Working with model APIs

4 hrs
  1. 3.1Hosted modelsOpenAI · Google Gemini · Anthropic Claude · API keys and setup
  2. 3.2Open modelsHugging Face · running models locally with Ollama
  3. 3.3Cost and limitstoken usage and monitoring · rate limits · streaming responses
04
Module 4

Prompt engineering

5 hrs
  1. 4.1Core techniquesinstruction-based prompting · zero-, one- and few-shot · role and system prompts
  2. 4.2Reasoning techniqueschain prompting · chain of thought · self-consistency · tree of thought
  3. 4.3Reliable outputverifying and controlling output · structured JSON output · prompt-injection basics
05
Module 5

LangChain essentials

6 hrs
  1. 5.1Framework basicswhat LangChain is · key components and modules
  2. 5.2Prompts and chainsprompt templates · chains and their uses · output parsers
  3. 5.3Conversations and safetymemory · moderating responses · handling hallucinations
06
Module 6

Building LLM applications

5 hrs
  1. 6.1Text applicationssentiment analysis · text classification · summarisation of long documents
  2. 6.2Information extractionextracting structured data from documents · PDF and OCR input
  3. 6.3Apps people can usechatbots · customer-service assistants · Streamlit front ends
07
Module 7

Embeddings and vector databases

4 hrs
  1. 7.1Embeddingsembedding models · similarity search · chunking strategies
  2. 7.2Vector storesChroma, FAISS and pgvector · metadata filtering · hybrid search and re-ranking
08
Module 8

Retrieval-augmented generation (RAG)

6 hrs
  1. 8.1Why RAGin-context vs external knowledge · RAG pipeline architecture
  2. 8.2Building the pipelinedocument loaders · text splitters · embeddings and vector storage · retrievers
  3. 8.3Better answerscitations · conversation memory · evaluating retrieval quality
09
Module 9

Evaluation, fine-tuning and responsible AI

4 hrs
  1. 9.1Evaluating LLM appstest sets · faithfulness and relevance · LLM-as-judge · RAGAS
  2. 9.2Fine-tuningwhen to fine-tune vs prompt vs RAG · LoRA on a small open model
  3. 9.3Responsible AIguardrails · handling personal data · bias and safety
10
Module 10

Capstone project

9 hrs
  1. 10.1Plan the solutionuse case · data sources · evaluation plan
  2. 10.2Build and evaluateLLM pipeline · Streamlit or web front end · evaluation report
  3. 10.3Demo and reviewlive demonstration · review feedback

Total duration: 50 hours. Training hours across ten modules, including guided labs and the capstone project.

Practical learning

Learn by building

  • A prompt library that turns messy text into clean JSON.
  • Sentiment, classification and summarisation apps with LangChain output parsers.
  • A Streamlit chatbot with memory and moderated responses.
  • A "chat with your documents" RAG app with citations, scored with RAGAS.

Projects

  • Mini project · Vendor quotation scorerExtract prices, taxes and terms from vendor quotations, then score and compare suppliers.
  • Major project · Resume onboarding assistantParse uploaded resumes into structured profiles, score them and suggest improvements.
  • Capstone · choose oneA bank-statement analyser that classifies transactions, a college-policy assistant using RAG, or a project of your own approved by the trainer.

Outcomes

What you can do after the course

Build LLM apps

Design and build applications on hosted and open models.

Ground answers in data

Build RAG systems that cite their sources.

Measure quality

Evaluate outputs and improve them with evidence.

Use AI responsibly

Control cost, protect personal data and add guardrails.

Prompt engineeringLLM APIsLangChainEmbeddingsRAGStreamlitEvaluation

Register

Join the waitlist for Generative AI

Registrations for this course aren't open right now. Leave your details and we'll email you first, with the batch dates, fees and next steps.

  1. 1Join the waitlist
  2. 2We email you as soon as registrations open
  3. 3You receive the batch dates, fees and next steps
Course brochure (PDF)Overview, the full syllabus with hours, projects and outcomes.Open the PDF

Registered & approved

  • MSME registeredUdyam-registered enterprise, Government of India
  • AICTE partnerApproved partner of the All India Council for Technical Education

Join the waitlist

Program: Generative AI

Preferred mode

We'll reply by email or phone with the next steps. By registering you agree to be contacted about this program.

Questions about Generative AI?

Email us with your background and goals and we'll help you choose the right course.

All courses

We use cookies to personalise your experience and to analyse our website traffic.
By clicking “Accept cookies”, you consent to our use of cookies.

View privacy policy