Quiz me — From Vectors to AI APIs

Q1.Which fact about "Embeddings — what they are, cosine similarity, use cases" matches the mechanism the module covered?

Q2.Which of these correctly identifies the role of "HuggingFace in 10 lines — pipeline, tokenizer, model" in the broader system?

Q3.When applying "HuggingFace in 10 lines — pipeline, tokenizer, model" in practice, which of these holds?

Q4.Which statement about how "Why transformers replaced everything — the context window insight" actually works is correct?

Q5."Fine-tuning vs prompting — when to do which" — which of these claims is supported by the module?

Q6.Which of these correctly identifies the role of "Why transformers replaced everything — the context window insight" in the broader system?

Q7.Which statement about how "Your first RAG pipeline — chunk, embed, store, retrieve, generate" actually works is correct?

Q8.When applying "Putting it together — a minimal AI feature from API to user" in practice, which of these holds?

Q9.For "Evaluating AI systems — BLEU, ROUGE, LLM-as-judge, human eval", which detail or constraint from the module is accurate?

Q10.For "BERT vs GPT — encoder-only vs decoder-only tradeoffs", which detail or constraint from the module is accurate?