Professional Skill Course

Generative AI Course in Nagpur

Move from prompt user to AI product builder — master LLMs, RAG pipelines, vector databases, and production deployment of Generative AI applications in Nagpur.

8 weeks (64 hours of instruction)

Offline Nagpur · Online · Hybrid

Course Completion Certificate — Skilleze Technologies

1-on-1 Mentorship Included

Key Facts SummaryExtractable Entity Specifications

Institute EntitySkilleze Technologies

Location & CampusNagpur, Maharashtra (Ramdaspeth / Central Nagpur)

Training & Delivery ModeOffline — Flat no. 8A, 2nd Floor, Kanchana Kiran Apartment, Ramdaspeth, Nagpur - 440010 · Online live (Zoom) · Hybrid

Program Duration8 weeks (64 hours of instruction)

Credential AwardedCourse Completion Certificate — Skilleze Technologies

Quick Answer

The Generative AI course in Nagpur covers LLM fundamentals, advanced prompt engineering, OpenAI and Gemini APIs, embeddings, vector databases, RAG pipeline architecture, fine-tuning basics, evaluation, AI guardrails, and production deployment. It is designed for developers, data analysts, and technically curious professionals who want to build and ship real Generative AI applications — not just use AI tools passively.

Course Specifications at a Glance

Generative AI course specifications
Duration	8 weeks (64 hours of instruction)
Weekly Hours	8 hours (weekday or weekend batch)
Mode	Offline — Flat no. 8A, 2nd Floor, Kanchana Kiran Apartment, Ramdaspeth, Nagpur - 440010 · Online live (Zoom) · Hybrid
Batch Timings	Weekday Morning: Mon–Fri 10:00 AM – 12:00 PM Weekday Evening: Mon–Fri 6:30 PM – 8:30 PM Weekend Batch: Sat–Sun 9:00 AM – 1:00 PM
Prerequisites	Python basics (functions, loops, file I/O). Students who completed the Full Stack Python or Data Analytics course are well-prepared. Non-developers with strong Python scripting skills are welcome.
Certificate	Course Completion Certificate — Skilleze Technologies
Fees	Fees on enquiry — speak to an advisor

Who Is This Course For?

Students

B.E. / B.Tech CS, IT, or related branches with Python experience
MCA or M.Sc. CS students wanting cutting-edge AI product-building skills
Data science students who want to add LLM/RAG skills to their profile
Students who want to work in AI-native startups after graduation
Any student in Nagpur who can write Python and is curious about how ChatGPT actually works

Working Professionals

Python or JavaScript developers wanting to integrate AI into their products
Data analysts or ML engineers who want to work with LLMs and vector databases
Product managers or technical leads who want to evaluate and architect AI solutions
Working professionals wanting to build an AI-focused portfolio in the hottest job market segment
Weekend-batch learners from any background who write Python and want to build AI products

Week-by-Week Syllabus — Generative AI

8 modules · 8 weeks (64 hours of instruction)

Module 1LLM Fundamentals — How Generative AI Works

Week 1

Transformer architecture overview: attention mechanism, tokens, and embeddings
Pre-training, fine-tuning, and RLHF: how ChatGPT and Gemini are built
Tokens and tokenisation: why token count matters for cost and context
Context window: what it is, its limits, and how models use it
Model families: GPT-4o, Gemini 1.5 Pro, Claude, Llama, Mistral — a comparison
Hallucination, bias, and why LLMs are probabilistic, not deterministic
Practical impact of temperature, top-p, and sampling parameters

PythonJupyter NotebookHugging Face (demo)

Outcome: Explain how a large language model generates text, why hallucinations occur, and how context window size and temperature affect output quality.

Module 2Advanced Prompt Engineering

Week 2

Zero-shot, few-shot, and many-shot prompting with examples
Chain-of-Thought (CoT) prompting and self-consistency techniques
System prompts: role, instructions, output format, constraints
Structured output: prompting for JSON, markdown tables, and consistent formats
Tree-of-Thought and ReAct (Reason + Act) prompting patterns
Prompt injection attacks and defensive prompting strategies
Prompt versioning and A/B testing prompts for production quality

OpenAI PlaygroundGoogle AI StudioPromptLayer

Outcome: Write system prompts and few-shot examples that produce consistent, structured, high-quality LLM outputs — and detect and mitigate prompt injection attempts.

Module 3OpenAI & Gemini APIs — Building AI Features

Week 3

OpenAI API: chat completions, function calling, streaming responses
Google Gemini API: multimodal inputs (text + image), grounding with search
Structured output with response_format (JSON mode) and Pydantic parsing
Tool/function calling: defining tools, handling tool results, multi-turn conversations
Vision models: analysing images, screenshots, and documents with GPT-4o / Gemini
Rate limiting, error handling, and retry strategies for production API calls
Cost estimation and token optimisation strategies for real applications

OpenAI Python SDKGoogle Generative AI SDKFastAPIPostman

Outcome: Build a FastAPI backend that exposes an AI feature using OpenAI or Gemini function calling — with structured JSON output, vision support, and rate-limit-aware error handling.

Module 4Embeddings & Semantic Search

Week 4

What are embeddings: vector representations of meaning in high-dimensional space
Text embedding models: text-embedding-3-small, all-MiniLM-L6-v2, BGE
Cosine similarity and dot product: measuring semantic distance between texts
Building a semantic search engine from scratch with embeddings
Embedding documents, queries, and comparing with numpy
Chunking strategies for long documents: fixed-size, recursive, semantic chunking
Evaluating embedding quality: retrieval precision, recall, MRR metrics

OpenAI Embeddings APIsentence-transformersnumpyscikit-learn

Outcome: Build a semantic search system that finds the most relevant document passages for a natural language query using embeddings and cosine similarity.

Module 5Vector Databases — Pinecone & Chroma

Week 5

Why vector databases: beyond keyword search, scalable similarity search
Chroma: local persistent vector store, collection management, metadata filtering
Pinecone: cloud-managed vector DB, namespaces, upsert, query, and delete
HNSW and IVF indexing algorithms: understanding the speed/recall tradeoff
Hybrid search: combining vector similarity with keyword (BM25) search
Metadata filtering: combining semantic search with structured filters
pgvector: vector similarity search inside PostgreSQL for simpler stacks

Chroma DBPineconeLangChain (retriever layer)pgvector (intro)

Outcome: Index a document corpus in both Chroma (local) and Pinecone (cloud), query with metadata filtering, and measure retrieval quality between the two setups.

Module 6RAG Pipelines — Retrieval-Augmented Generation

Week 6

RAG architecture: document ingestion → chunking → embedding → retrieval → generation
LangChain RAG chain: RetrievalQA, ConversationalRetrievalChain
LlamaIndex query engine: document loading, indexing, retrieval modes
Advanced RAG: re-ranking, HyDE (Hypothetical Document Embeddings), multi-query
Chat memory: ConversationBufferMemory, ConversationSummaryMemory
Multi-document RAG: routing queries to different knowledge bases
Exposing a RAG pipeline as a FastAPI endpoint for a React frontend

LangChainLlamaIndexChroma / PineconeFastAPI

Outcome: Build and deploy a production-quality RAG pipeline that answers questions over a private document corpus using LangChain or LlamaIndex, exposed as a REST API.

Module 7Fine-Tuning Basics, Evaluation & Guardrails

Week 7

When to fine-tune vs few-shot vs RAG: the decision framework
OpenAI fine-tuning: JSONL dataset format, uploading, training, and evaluation
PEFT: LoRA and QLoRA for fine-tuning open-source models on limited hardware
RAG evaluation with RAGAS: faithfulness, answer relevancy, context precision
LLM evaluation: G-Eval, LLM-as-judge patterns, human evaluation rubrics
AI guardrails: output validation, topic restriction, PII detection with Guardrails AI
Observability: tracing LLM calls with LangSmith for debugging production issues

OpenAI Fine-tuning APIRAGASGuardrails AILangSmith

Outcome: Fine-tune a small GPT model, evaluate a RAG pipeline with RAGAS metrics, and add input/output guardrails to an AI application before production deployment.

Module 8Production Deployment & Capstone

Week 8

Streamlit for rapid AI app prototyping: building a chat UI in 50 lines
FastAPI production setup: async endpoints, streaming responses with Server-Sent Events
Dockerising an AI application: managing model clients, environment secrets
Deploying to Hugging Face Spaces, Railway, or Render with environment variables
Cost monitoring: tracking API spend, setting usage limits, optimising prompt tokens
Responsible AI considerations: transparency, disclosure, and avoiding harm
Capstone project: full AI application from RAG pipeline to deployed web UI

FastAPIDockerHugging Face SpacesRailwayStreamlit

Outcome: Deploy a complete Generative AI application — RAG pipeline + API + chat UI — to a live public URL with observability, guardrails, and cost monitoring in place.

Tools & Technologies You Will Master

Python 3.12

OpenAI API (GPT-4o)

Google Gemini API

LangChain

LlamaIndex

Chroma DB

Pinecone

sentence-transformers

RAGAS

Guardrails AI

LangSmith

FastAPI

Streamlit

Docker

Hugging Face Spaces

Language Framework Database DevOps AI Platform

Capstone Projects — What You Will Ship

Private Document Q&A Assistant

Project 1

Problem: Build a chatbot that answers questions over a private PDF corpus (e.g., company policies, textbook chapters) — with accurate citations and hallucination-aware guardrails.

LangChainChromaOpenAI GPT-4oFastAPIReactRAGAS evaluation

You ship: A live-deployed RAG chatbot with source citations, evaluated with RAGAS, guarded against off-topic queries, and accessible via a React chat UI on a public URL.

AI-Powered Resume Screener

Project 2

Problem: Create a tool that takes a job description and a batch of resume PDFs, embeds them, and ranks resumes by semantic fit — then explains each ranking with LLM-generated summaries.

Pythonsentence-transformersPineconeGPT-4oStreamlitDocker

You ship: A Dockerised Streamlit app deployed on Hugging Face Spaces that accepts job descriptions and PDFs and returns ranked, LLM-explained shortlists — fully shareable portfolio project.

Multimodal Product Catalogue Assistant

Project 3

Problem: Build an assistant that accepts product image uploads + customer questions and uses Gemini vision to answer questions about product specs, compatibility, and comparisons.

Gemini API (Vision)FastAPIReactRailwayGuardrails AI

You ship: A deployed vision-powered product assistant with topic guardrails, streaming responses, and a React chat interface — demonstrating multimodal AI in a product context.

Career Outcomes — Where This Course Takes You

Target Role Titles

AI Engineer

Generative AI Developer

LLM Application Engineer

Prompt Engineer

AI Solutions Developer

RAG / Knowledge Base Engineer

Skills You Will Reach

Skills matrix for Generative AI
Skill	Level	Indicator
LLM Fundamentals & Prompt Engineering	Advanced
OpenAI & Gemini API Integration	Advanced
Embeddings & Semantic Search	Proficient
Vector Databases (Chroma / Pinecone)	Proficient
RAG Pipeline Architecture	Proficient
LLM Evaluation (RAGAS)	Foundational
AI Guardrails & Safety	Foundational
Production AI Deployment	Foundational

Sample Interview Questions You Will Be Ready For

“What is Retrieval-Augmented Generation and why is it preferred over fine-tuning for private knowledge bases?”
“How do embeddings represent semantic meaning, and how does cosine similarity work?”
“What are the tradeoffs between Chroma (local) and Pinecone (cloud) for a vector store?”
“How do you evaluate whether your RAG pipeline is actually returning faithful answers?”
“What are the main risks of deploying an LLM application and how do you mitigate them with guardrails?”

Salary benchmarks: <<PLACEHOLDER: Average salary for AI Engineers / Generative AI Developers in India — source: AmbitionBox / Glassdoor India, verified [month year]>>

Why Skilleze Technologies — Not Just Another Institute

Skilleze Technologies vs generic institutes comparison
What You Get	Skilleze Technologies	Generic Institutes
Mentorship	1-on-1 mentor sessions + PR code reviews	Recorded videos only
Projects	2–3 deployed capstone projects with live URL	Toy exercises or no projects
Syllabus currency	Updated to 2025–26 industry tooling	Often 2–3 years behind market
Batch size	Small cohorts — mentor access is real	Large batches, no individual feedback
Certificate verifiability	Verifiable reference number issued	No verification mechanism
Location	Offline Nagpur + online + hybrid	Online only or fixed city only
Career layer	ATS resume + LinkedIn + mock interviews	Not included

Comparisons are factual statements about our own offering. We do not name or endorse any specific competitor.

Frequently Asked Questions — Generative AI

Is Generative AI worth learning in 2026?

Generative AI is the fastest-growing technical skill category globally. Every software product is integrating AI features — from search to customer service to developer tools. Professionals who can build RAG pipelines, integrate LLM APIs, and evaluate AI outputs are in extremely high demand. In 2026, AI engineering skills have premium salaries and very low supply.

What is the fee for the Generative AI course in Nagpur?

Fees are shared during a personal advisor call. EMI plans are available. Connect via WhatsApp or the enquiry form — an advisor will share the complete fee structure within one business day.

Do I need to know machine learning to take this Generative AI course?

No. This course does not require prior ML or deep learning experience. You need Python basics — functions, loops, file I/O. Machine learning theory is explained as context where needed, but the focus is on using LLM APIs, building RAG pipelines, and deploying AI applications — not training neural networks from scratch.

What is RAG and why is it important?

Retrieval-Augmented Generation (RAG) is a technique where you give an LLM access to a private knowledge base by retrieving relevant document chunks at query time and including them in the prompt. It is important because it allows you to build AI applications that answer questions accurately from your own data — without fine-tuning or risking hallucinations from the model's outdated training data.

Does this course cover OpenAI GPT-4o and Google Gemini?

Yes. Week 3 covers both the OpenAI Python SDK (GPT-4o, function calling, streaming, vision) and the Google Generative AI SDK (Gemini 1.5 Pro, multimodal inputs, grounding). You build projects using both APIs so you are not locked into one provider.

Is vector database knowledge important for AI jobs?

Yes, increasingly so. Vector databases (Chroma, Pinecone, Weaviate, pgvector) are the foundation of almost every production RAG system. Week 5 covers two vector stores — Chroma for local development and Pinecone for cloud-scale — including metadata filtering, hybrid search, and indexing strategy.

Is this Generative AI course available offline in Nagpur?

Yes. Offline classes at our Wardha Road centre in Nagpur. Online live Zoom and hybrid options also available. Weekend batches run Saturday–Sunday for working professionals.

How is this course different from watching AI tutorial videos on YouTube?

This course is structured around building complete, deployed projects — not watching demos. You build a RAG chatbot, an AI resume screener, and a multimodal assistant — each with evaluation, guardrails, and a live URL. Mentor code reviews help you identify and fix real architectural issues that tutorial videos never show.

Can non-developers take this Generative AI course?

The course requires Python basics — if you can write a Python function and understand loops and dictionaries, you can participate. Data analysts with Python experience are excellent candidates. Pure non-technical roles (no Python at all) would be better served by the Automation course first to build scripting skills.