C.W.K.
Stream
Quiz · 4 questions

📥 The Ingest Boundary

How text gets in — chunk it, adapt it, clean it at the seam

Level 0Unlit Wick
0 XP0/33 lessons0/12 achievements
0/100 XP to next level100 XP to go0% complete

Quiz

01A chunk carries char_start and char_end offsets. What are they offsets INTO, and why does that choice matter?
02When one document in a corpus changes, what is the smallest thing the index mutates?
03What distinguishes a 'referenced' adapter from a 'captured' adapter at ingest time?
04A corpus of web content produced junky completions full of HTML attribute fragments. What was the correct fix?
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.