Lab 1: Tokenization Methods with Python
Build a strong foundation in NLP preprocessing by analyzing and comparing tokenization techniques such as Byte Pair Encoding (BPE) and SentencePiece, focusing on efficiency, rare-word handling, and cost optimization for AI workloads.

Lab 2: LLM Text Generation Parameters
Understand how to optimize model responses by experimenting with temperature, top-p, max tokens, and penalties to control creativity, determinism, response length, and inference cost.

Lab 3: Prompt Engineering for Reasoning and Structured Outputs
Develop advanced prompting skills using zero-shot, one-shot, few-shot, Chain of Thought (CoT), Tree of Thought (ToT), and role-based prompting to solve reasoning tasks and generate structured outputs such as JSON, summaries, classifications, and code.

Lab 4: Building LLM Applications with LangChain
Create intelligent AI-powered applications using LangChain by integrating conversation memory, translation, summarization, tools, and retrieval-based question answering (RAG) for context-aware enterprise solutions.

Lab 5: Simple LLM-Powered Application with Streamlit
Build an interactive Streamlit-based application connected to LLM APIs with dynamic prompts, UI controls, and parameter tuning for real-time AI use cases.

Lab 6: Generative Visual AI
Explore multimodal AI by generating images with DALL·E and Stable Diffusion, while using BLIP for image captioning and visual understanding tasks.