SproutStack🌱 AI Engineering · Your First AI App · cozy lesson
Structured Output from LLMs 🔒 premium preview
🔒 Marked premium for future. Free while we build locally — payment comes later.
10 min · 1 min read · no scary math, promise
🤖
You’ve got this. Read a little, play a little — I’ll wait. No rush.
resp = client.chat.completions.create(
model="gpt-4o-mini",
response_format={"type":"json_object"},
messages=[{"role":"user","content":'Return {"title":str,"priority":"low|high"}'}],
)
import json; from pydantic import BaseModel
class T(BaseModel): title:str; priority:str
print(T.model_validate(json.loads(resp.choices[0].message.content)))
Prompt: field names, enums, example. Retry once with error message if invalid.
💛 Enjoying? Try 5 playful quizzes or watch it move.
Check your understanding
Correct answers earn XP (once each).
1. Why JSON mode?
2. Validate with…
My notes (saved in this browser)
Select text above → Save selection, or write your own. AlgoMaster-style notebook, local-first for MVP.
No notes yet. Your highlights will live here.
Finished reading? Seal it with a tick ✅
The checkbox in the explorer turns green too — same progress.