GenAI-Learnings

October 5, 2025 · View on GitHub

Welcome to GenAI-Learnings, a curated hub of resources, projects, and experiments exploring the world of Generative AI. This repository is designed for AI engineers, enthusiasts, and learners who want to explore everything from autonomous agents to NLP, computer vision, vector databases, and practical project implementations.

"Learning AI is fun… but learning Generative AI is like teaching a robot to daydream!" 😄

Explore more of my work:

Complete Data Science: A deep dive into Data Science AI concepts, tools, and projects and all the material for learning and interview preparation.
LangChain-Mastery: Everything you need to master LangChain for building powerful LLM applications.
MCP-YFinance-Server: A backend service for financial analytics and modeling.
Reinforcement-Learning: Hands-on experiments and theory in Reinforcement Learning.
CompleteRAG: End-to-end implementation of Retrieval-Augmented Generation (RAG) systems.

Agentic AI

Hands-on notebooks for autonomous agents using SmolAgents and other frameworks:

Coffee_Ordering_Bot.ipynb – Simple agent that takes coffee orders
First Agent.ipynb – Stock market agent using Agno
Party_Agent_smolagents.ipynb – Party-themed agent example
Stock Market Agent.ipynb – Advanced stock market agent

Computer Vision

Experiments and tutorials on generative AI applied to images:

AutoEncoders.ipynb – Exploring autoencoders for image reconstruction
CNN.ipynb – Convolutional Neural Networks basics and applications
Transfer_learning.ipynb – Transfer learning with pretrained models

Data Preprocessing

Guides and notebooks for text preprocessing and feature engineering:

Beginner's_Text_Preprocessing.ipynb – Basic text preprocessing
Text_Classification_ML.ipynb – ML-based text classification preprocessing
Text_Representation.ipynb – Feature representation for NLP tasks

Encodings

Tokenization and encoding techniques for NLP:

Byte_Pair_Encoding_tokenization.ipynb – Byte Pair Encoding tutorial
Tokenizer.ipynb

HuggingFace

Fine-tuning, transformer pipelines, and practical NLP projects:

Fine_tuning_masked_model.ipynb – Fine-tune a masked language model
Finetuned_on_AgNews.ipynb – DistilBERT fine-tuned on AgNews dataset
Fully_trained_bert_on_mrpc.ipynb – BERT-base-uncased on MRPC dataset
HuggingFace_Transformers.ipynb – HuggingFace pipeline exploration
Text_Summarization_Project.ipynb – End-to-end text summarization
Text_to_Image_Generation.ipynb` – Basic text-to-image generation
Translation.ipynb – Machine translation experiments

Vector Databases

Notebooks for vector database usage and embeddings:

ChromaDB.ipynb – Chroma database experiments
Pinecone.ipynb – Pinecone vector DB integration

Prompt Engineering

Notebooks for designing and experimenting with prompts:

COT_Prompting.ipynb – Chain of Thoughts (CoT) prompting
Few_Shot_Prompting.ipynb – Few-shot learning with prompts
Zero_Shot_Prompting.ipynb – Zero-shot learning experiments

Quantization

Techniques for compressing and optimizing models:

AQLM_Quantization.ipynb – Quantization methods
AWQ_Quantization.ipynb – Advanced quantization experiments

PlayBook

Guides and small projects to apply generative AI concepts:

Anomaly_detection_with_embeddings.ipynb – Embedding-based anomaly detection
Browser_as_tool_with_LLM.ipynb – Using browser tools with LLMs
Gemini_Intro.ipynb – Introduction to Gemini AI

Interview Questions

Curated questions and answers for LLM and NLP interviews:

100_LLM_INTERVIEW_QUESTIONS.md – 100 essential LLM interview questions
NLP_interview_questions.md – NLP-focused interview questions

Small Projects

🎯 Key Features

Comprehensive hands-on notebooks covering generative AI concepts and applications
Includes agent-based AI, computer vision, NLP, vector databases, and small projects
Focus on practical learning, experimentation, and project-ready skills
Integrated HuggingFace Transformers, fine-tuning, prompt engineering, and quantization
Curated interview preparation material and reusable playbooks

🛠️ Tech Stack

Programming Languages: Python
Libraries & Frameworks: PyTorch, Transformers, HuggingFace, SmolAgents, FastAPI
Data & NLP Tools: Pandas, NumPy, NLTK, SpaCy
Vector Databases: ChromaDB, Pinecone
Deployment & MLOps: Docker, MLflow, DVC, AWS

🤝 Contributing

Contributions are welcome! Feel free to fork the repository, raise issues, and submit pull requests.