← Simulators

🎯 Mental Model

Full stack from raw text to LLM generation.

The full pipeline from raw text to LLM output. Each step is covered in the guide.

Full AI stack

Raw Text
Normalization
Tokenization
Token IDs
Embeddings (Vectors)
Vector Database
Similarity Search
LLM Generation

Explore by topic

  • Ch 2 — Text → Tokens → IDs
  • Ch 3 — Normalization
  • Ch 8 — Embeddings
  • Ch 10 — RAG / Vector search
  • Simulator — Embeddings & similarity