{
  "lesson": "23-chunking-strategies-rag",
  "title": "Chunking Strategies for RAG",
  "questions": [
    {
      "stage": "pre",
      "question": "Why is chunking strategy as important as the embedding model in RAG?",
      "options": [
        "Chunking shrinks the model",
        "Smaller chunks train faster",
        "Chunking is required by FAISS",
        "Chunk boundaries determine whether the answer is even retrievable; bad chunks defeat any embedding"
      ],
      "correct": 3,
      "explanation": "Vectara's 2025 study showed chunking quality matches or exceeds embedding-model impact on retrieval quality."
    },
    {
      "stage": "pre",
      "question": "What does LangChain's RecursiveCharacterTextSplitter try in order?",
      "options": [
        "Try splitting on paragraph breaks, then newlines, then sentence boundaries, then spaces",
        "Split on token IDs",
        "Split on whitespace only",
        "Always split on character N"
      ],
      "correct": 0,
      "explanation": "Recursive splitting falls back through paragraph -> newline -> sentence -> space to preserve structure."
    },
    {
      "stage": "check",
      "question": "Why does the parent-document pattern improve answer quality?",
      "options": [
        "It removes embeddings",
        "Children give precise retrieval; returning the larger parent block preserves the surrounding context the reader needs",
        "It avoids tokenization",
        "It uses fewer GPU cycles"
      ],
      "correct": 1,
      "explanation": "Retrieve by small child chunks for precision, then expand to the parent for context."
    },
    {
      "stage": "check",
      "question": "What does Anthropic's 'contextual retrieval' add to each chunk before indexing?",
      "options": [
        "An LLM-generated 50-100 word summary placing the chunk in the document's overall context",
        "Random noise",
        "A POS tag",
        "A language code"
      ],
      "correct": 0,
      "explanation": "Contextual retrieval prepends an LLM-written situating summary to each chunk; ~35-50% recall gain."
    },
    {
      "stage": "check",
      "question": "Which 2026 finding contradicts the conventional wisdom about chunk overlap?",
      "options": [
        "Overlap should be 50%",
        "Overlap is required for BM25",
        "Overlap improves contextual retrieval only",
        "Empirical 2026 benchmarks show overlap often provides zero measurable benefit while doubling index cost"
      ],
      "correct": 3,
      "explanation": "Newer studies (SPLADE+Mistral on NQ) show chunk overlap rarely helps and inflates index size."
    },
    {
      "stage": "post",
      "question": "Which chunk size does NVIDIA's 2026 benchmark associate with factoid queries?",
      "options": [
        "Roughly 256-512 tokens",
        "2048-4096 tokens",
        "8192 tokens",
        "64 tokens"
      ],
      "correct": 0,
      "explanation": "Factoid queries benefit from smaller chunks (256-512 tokens) that concentrate the answer signal."
    },
    {
      "stage": "post",
      "question": "Why is a min-token floor important when using semantic chunking?",
      "options": [
        "Without a floor, semantic chunking can produce tiny 40-token fragments that hurt retrieval",
        "Required by BERT",
        "Floors prevent overlap",
        "Floors speed up inference"
      ],
      "correct": 0,
      "explanation": "Semantic chunkers can over-segment; enforcing a min size prevents low-signal fragments."
    },
    {
      "stage": "post",
      "question": "What does 'late chunking' do differently from traditional chunking?",
      "options": [
        "Chunks after retrieval",
        "Embeds the whole document at the token level first, then pools token embeddings into chunk vectors to preserve cross-chunk context",
        "Skips chunking entirely",
        "Uses BM25 instead"
      ],
      "correct": 1,
      "explanation": "Late chunking embeds first and pools second, preserving contextual interactions across chunk boundaries."
    }
  ]
}