Quiz · 4 questions
🧩 Chunking and Ingestion
How you slice the corpus decides what you can find
Level 0Scout
0 XP0/41 lessons0/10 achievements
0/120 XP to next level120 XP to go0% complete
Quiz
01Why does embedding a whole 10-page document as one vector usually hurt retrieval quality?
02You split with a character-based splitter at 1200 chars. The same chunk is 240 tokens in English and 700 tokens in Korean. What is the consequence for an 8192-token model?
03When does structure-aware splitting (Markdown headers, code AST) outperform a generic recursive splitter?
04What is the single biggest production performance win that disciplined metadata enables?
Comments 0
🔔 Reply notifications (sign in)Sign in — Please sign in to comment.
No comments yet — be the first.