Building LLM Applications

Tokens, context windows, prompting, structured outputs and function calling

Understand LLMs from the inside out: tokenisation, context windows, prompting, structured outputs, function calling, streaming and multimodal inputs. The foundation for everything generative.

Skills you'll gain

LLM APIsPromptingStructured OutputsFunction CallingStreamingMultimodal

Prerequisites

PythonHTTP APIs

Chapters

LLM FundamentalsIntermediate

Tokens, context windows, model APIs, pricing and the mental model every AI engineer needs.

22m

Prompt EngineeringIntermediate

Structure, few-shot, structured outputs and function calling. Prompts are code — version them.

30m

Streaming & Structured OutputsAdvanced

SSE streaming, incremental JSON parsing, and reliable structured output at production scale.

34m

Local & Open-Source ModelsAdvanced

Ollama, LM Studio, Hugging Face, Llama, Mistral, Gemma, Qwen — when and how to self-host models.

32m

Fine-Tuning FundamentalsExpert

LoRA, QLoRA, full fine-tuning, when to fine-tune vs RAG, and the economics of customisation.

34m

Labs in this series

Call an LLM with Structured Output

Intermediate

Implement call_structured() that returns a validated Pydantic model from an LLM, with retry on validation failure.

40m4 skills