☕ Learning path
Learn AI Infrastructure.
The plumbing behind every AI feature: how text becomes tokens and vectors, and how models are grounded in real data.
0 of 7 steps
New to the lingo? Every AI reads text as tokens, and only so many fit in its context window at once. To work with more, text is turned into embeddings and stored in a vector database the model can search. Hover any underlined word for a quick definition, or click to learn more.
- ReadWhat is a context window? The model's working memory, tokens, what fills it, why it runs out, and how to manage it.
- Trytoken counter Count tokens with the real OpenAI tokenizers.
- ReadWhat are embeddings? How content becomes a vector that captures meaning, the engine behind semantic search, RAG, and recommendations.
- Tryembedding explorer Real embeddings + semantic search, in-browser.
- ReadWhat is a vector database? Where embeddings live, fast nearest-neighbour search over millions of vectors, and the backbone of RAG.
- ReadWhat is RAG (Retrieval-Augmented Generation)? Grounding a model in your own documents at query time, embeddings, retrieval, and why it beats fine-tuning for facts.
- Tryrag chunking visualizer See how a document splits into RAG chunks.
Capstone · build it
Trace a real question through the stack
Pick a question you would actually ask an AI. Now follow it through the machinery you just learned, using the tools from this path. Progress saves on this device.
0/5
Tools for the job: Token CounterEmbedding ExplorerRAG Chunking Visualizer
🎉 Capstone complete. You didn’t just read it, you did it.
More routes: all learning paths, the skill tree, or the knowledge map.