Workshop materials for "From Zero to Hero: How to put GPT LLMs & friends into your applications - Generative AI in Action"
A hands-on masterclass teaching how to integrate Generative AI and Large Language Models into applications. Covers key architectural patterns including In-Context Learning, RAG, Structured Output, Tool Calling, and ReAct.
- Human language as interface for software (prompts as UI)
- LLM basics with Python and .NET APIs
- RAG (Retrieval-Augmented Generation)
- Function/Tool Calling
- Structured Output
- ReAct (Reasoning & Acting) agents
- Speech-to-text integration
Demos/ # Live demonstration code
Hello World/ # Basic LLM integration (LangChain, Semantic Kernel, OpenAI SDK)
Function Calling/ # Tool calling examples (LangGraph, Semantic Kernel)
Information Extraction/ # Voice orders, flight query extraction
RAG/ # Embeddings, vector DB, retrieval patterns
ReAct/ # Barebones ReAct agent implementation
Hands-on/ # Workshop exercises with solutions
chat/ # Simple chat lab
function_calling/ # Tool calling lab
structured_output/ # Extraction lab
vector_db-and-rag/ # RAG lab
- Python: LangChain, LangGraph, OpenAI SDK, Streamlit
- .NET/C#: Semantic Kernel, OpenAI SDK
- Jupyter Notebooks for demos and labs
- Python 3.10+
- .NET 8.0+
- OpenAI API key (or Azure OpenAI)
- Clone the repository
- For Python projects:
pip install -r requirements.txtin respective folders - For .NET projects: Open
gen-ai-workshop.slnin Visual Studio - Copy
.env.exampleto.envand add your API keys
MIT