🌱 AI Engineering · Python for AI · cozy lesson
APIs, JSON and Pydantic
12 min · 1 min read · no scary math, promise
🤖
You’ve got this. Read a little, play a little — I’ll wait. No rush.
Flow
App → POST JSON → LLM → JSON back → validate → act.
import requests
from pydantic import BaseModel
class Ticket(BaseModel):
title: str
priority: str # low|high
r = requests.post("https://api.example.com/chat",
json={"messages": [{"role":"user","content":"hi"}]},
headers={"Authorization": "Bearer $KEY"}, timeout=30)
data = Ticket.model_validate(r.json()) # throws if bad
Always: timeouts, retries with backoff, log status codes, never ship keys in frontend.
💛 Enjoying? Try 5 playful quizzes or watch it move.
Check your understanding
Correct answers earn XP (once each).
1. Why Pydantic?
2. 401 vs 429?
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.