Gen-AI Engineering

Learn the simple differences between AI Engineering and ML Engineering roles, what they do daily, and which career path might work better for you.

Discover the fundamentals of Large Language Models (LLMs) - what they are, how they work, and why they're revolutionizing AI. Perfect introduction for developers entering the AI space.

Learn how to set up Google's Gemini AI model for development, including API key configuration and environment setup for your first LLM integration.

Make your first API call to Google's Gemini LLM using TypeScript. Learn the fundamentals of prompt engineering, handling responses, and understanding the request-response cycle.

Master the fundamentals of tokens in LLM applications. Learn what tokens are, how they work, and how to track actual token usage in your Gemini API calls.

Master the essential parameters that control LLM behavior across all major providers. Learn how temperature, max tokens, and other key settings shape your AI responses with practical TypeScript examples.

Build your first complete AI-powered CLI application using TypeScript and Gemini. Learn to create an interactive command-line assistant that demonstrates all the fundamentals you've learned in this module.

Master the art and science of crafting effective prompts to unlock the full potential of LLMs. Learn essential techniques, common patterns, and best practices for getting consistent, high-quality responses from AI models.

Learn the basics of maintaining conversation history with AI models. Understand how to keep track of user and AI messages to create simple chat experiences that remember previous exchanges.

Learn how to implement real-time streaming responses from AI models. Build interactive chat experiences where AI responses appear word by word, creating more engaging user interactions.

Build a sophisticated command-line chat assistant that combines conversation management with streaming responses. Learn to create a conversational AI that remembers context, maintains personality, and delivers responses in real-time for an engaging user experience.

Learn how to enable AI models to call external functions and tools with real-time streaming responses. Transform your conversational AI from simple chat to a powerful assistant that can perform calculations, fetch data, and execute specific tasks through structured function calls.

Learn to build AI assistants that can use multiple tools simultaneously. Master function selection, chaining calls, and creating realistic multi-tool scenarios with streaming responses.

Master structured data generation with AI. Learn to force consistent JSON outputs, validate data structures, and build reliable data processing pipelines with streaming responses.

Build a practical CLI assistant that combines conversation management with essential tools. Create a streamlined developer tool that handles calculations, file operations, and maintains conversation context throughout the session.

Learn what Retrieval-Augmented Generation (RAG) is, how it differs from traditional AI approaches, and why it's essential for building knowledge-aware AI applications.

Learn what text embeddings are, how they work, and how to create them using Google's Gemini API. Master the fundamental building blocks of RAG systems through hands-on TypeScript examples.

Implement vector storage and similarity search using simple in-memory vector stores for efficient document retrieval.

Learn to build complete RAG pipelines by combining retrieval mechanisms with generation for enhanced AI responses.

Build a complete document question-answering system using RAG techniques in this comprehensive CLI project.