Generative AI Crash Course

Sophia Jaymes

By Aman In Grow Data Skills

Self Paced
English
Completion Certificate

Watch demo class

1 Year

Validity (From the date of Enrollment)

30 Hours

Duration

13

Sessions

2

Projects

INR 3500

This course includes

Content Duration30 Hours
Total Video Sessions13
Total Industry Projects2
Project will be covered from scratch
Tools – Jupyter Notebook, Google Collab, PyCharm, Spyder, Visual Studio
Technology – OpenAI, Generative AI, Cloud, LLM, Computer Vision
Offline doubt support on private discord group
Certificate of completion

Show More

Tech stack you'll learn

GenAI Crash Course

Course Content

✅ Class 1: Understanding Generative AI

What is Generative AI? Why now?
Evolution from GPT-2 to GPT-4o, Claude, Gemini, Mistral, LLaMA
Generative AI vs Traditional AI
Popular use cases across industries

✅ Class 2: Transformers & Foundation Models

Transformer architecture: Encoder, Decoder, Encoder-Decoder
Pre-training vs Fine-tuning
Anatomy of Foundation Models
Overview of major LLMs: GPT, LLaMA, Claude, Gemini, Mixtral

✅ Class 3: Prompt Engineering & Text Generation

Prompt types: Zero-shot, Few-shot, Chain-of-Thought
Parameters: Temperature, Top-k, Top-p
Completion vs Chat mode
Tools: OpenAI Playground, Hugging Face Transformers

✅ Class 4: Hands-on Project 1 — AI Content Generator

Build a Streamlit or FastAPI app for blog/product/tweet generation
Prompt templates for tone, style, length
Deploy using OpenAI or Hugging Face LLMs

✅ Class 5: Text-to-Image & Image-to-Image Models

Diffusion Models: Stable Diffusion, DALL·E 3, Midjourney
Prompting for image generation
Text-to-image, inpainting, and image variation demos

✅ Class 6: Multimodal AI in Action

GPT-4o, Gemini 1.5, LLaVA, Flamingo overview
Text + image + audio + video models
Applications: Virtual Assistants, Search, Customer Service

✅ Class 7: Deep Dive into RAG

Why LLMs need RAG (context windows, hallucination)
Vector embeddings and similarity search
Vector DBs: FAISS, Chroma, Pinecone
Tools: LangChain, LlamaIndex

✅ Class 8: Hands-on Project 2 — Chat with Your PDFs

Upload PDF → extract text → embed → chat
FAISS + LangChain or LlamaIndex + Streamlit
Use OpenAI or LLaMA as the backend model

✅ Class 9: Fine-tuning LLMs & Parameter-efficient Training

When to fine-tune vs prompt-engineer
LoRA, QLoRA, PEFT explained
Tools: Hugging Face Trainer, OpenAI Fine-tune API
Dataset curation & model hosting

✅ Class 10: Agents & Tool Use

What are LLM agents?
LangChain Agents, OpenAI Function Calling
Autonomous agents: AutoGPT, BabyAGI
Use Cases: Report generation, browsing, scheduling

✅ Class 11: Deploying GenAI Apps

Build FastAPI, Streamlit, Gradio apps
Containerize with Docker
Hosting: RunPod, Replicate, Azure/AWS/GCP
Scalability & cost optimization tips

✅ Class 12: Risks, Ethics & Career in GenAI

Hallucination, bias, and safety concerns
Guardrails & moderation tools
Copyright & responsible AI
Career paths, portfolio building & trends for 2025

Building a Strong Analytics Engineer Portfolio
Resume Optimization for Data Roles
Preparing for Technical Interviews
Networking and Job Search Strategies

Tech Stack: Python, Transformers library, LangChain, OpenAI, Stream lit, Hugging Face models
Overview of Q&A systems and GenAI
Generative AI Fundamentals
Q&A System Architecture
Data Preparation
Building the Q&A Model
Creating the Chat Interface
Evaluation and Improvement
Deployment

Tech Stack: Python, Transformers library, spaCy, Pandas, Streamlit, Hugging Face models
Overview of financial data extraction
Introduction to LLMs and their capabilities
Financial Document Understanding
Information Extraction Techniques
Data Preparation
Implementing the Extraction Pipeline
Post-processing and Structuring
Evaluation and Optimization
Building a User Interface

Tech Stack: Python, Google's Gemini API, OCR library (e.g., Tesseract), OpenCV, Streamlit
Overview of invoice processing and information extraction
Gemini Model Architecture
Invoice Understanding
Data Preparation
Building the Extraction Pipeline
Post-processing and Validation
Creating a User Interface
Evaluation and Improvement

Tech Stack: Python, OpenAI API or Google's Vertex AI, stream lit, Git, GitHub API
Why automatic code analysis is important
Intro to Gen AI for code understanding
Challenges in analyzing code with AI
Preprocessing code for AI analysis
Building our analysis pipeline
Creating a user-friendly interface
Testing and improving our analyzer
Discussing real-world use and limitations

Course Schedule

Mode Of The Course:

Recorded

Course Duration:

30 Hours

Total Sessions:

13

Total Project:

2

Course Validity:

1 Year (From the date of enrollment)

Prerequisite:

Basic Python

⚠️ Important Notice :

The video may not work on Linux due to DRM restrictions. It is only accessible on Chrome when using Windows or macOS.

Workaround: To access the video on Linux, you can create a Windows virtual machine (VM) and watch the video through the VM. Alternatively, you can use our Android or iOS application to view the video on your mobile device.

Instructor

Aman Kumar

Aman, an experienced Data Scientist at EY, excels in turning data into impactful insights and solutions. Beyond his work, he's a certified IBM Instructor for IoT and AI, having mentored over 500 students in Data Science, NLP, ML, and AI. Aman's commitment to education and innovation showcases his passion for using data to drive positive change.

Generative AI Crash Course

INR 3500

Ask Shashank

Ask Shashank

Chat on WhatsApp Email support