rohitg00--ai-engineering-from-scratch
wehub-resource-sync
79 行
2.7 KiB
JSON
79 行
2.7 KiB
JSON
{
|
|
"lesson": "15-batch-apis",
|
|
"title": "Batch APIs — the 50% Discount as Industry Standard",
|
|
"questions": [
|
|
{
|
|
"stage": "pre",
|
|
"question": "What is the common batch-API offer across OpenAI, Anthropic, and Google in 2026?",
|
|
"options": [
|
|
"10% discount with 1-hour turnaround",
|
|
"90% discount with 7-day turnaround",
|
|
"Free if under 1k tokens",
|
|
"50% discount with 24-hour turnaround"
|
|
],
|
|
"correct": 3,
|
|
"explanation": ""
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "What does \"24-hour turnaround\" actually guarantee in the lesson's framing?",
|
|
"options": [
|
|
"24h is the cache TTL",
|
|
"The batch always takes 24 hours",
|
|
"The provider promises to return within 24 hours, with typical P50 around 2-6 hours",
|
|
"Only batches under 1k requests qualify"
|
|
],
|
|
"correct": 2,
|
|
"explanation": ""
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "How does stacking batch with cached input change the bill versus synchronous uncached on a shared-system-prompt workload?",
|
|
"options": [
|
|
"It has no effect because caching is automatic",
|
|
"It only helps if the model is on Vertex",
|
|
"It can drop to roughly 10% of the synchronous-uncached baseline",
|
|
"It increases cost by 50%"
|
|
],
|
|
"correct": 2,
|
|
"explanation": ""
|
|
},
|
|
{
|
|
"stage": "check",
|
|
"question": "Which workload-triage lane is wrong to default to in 2026 for content pipelines and offline labeling?",
|
|
"options": [
|
|
"Interactive, because it sounds urgent",
|
|
"Batch, because the user does not see a 24h delay",
|
|
"Hybrid batch-and-cache",
|
|
"Semi-interactive with async queue"
|
|
],
|
|
"correct": 0,
|
|
"explanation": ""
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "What is the output-schema trap across providers?",
|
|
"options": [
|
|
"JSONL is unsupported by Anthropic",
|
|
"All providers use the same OpenAI JSONL format",
|
|
"Vertex requires Parquet only",
|
|
"Batch file formats differ per provider (OpenAI JSONL, Anthropic JSONL, Vertex BigQuery/GCS), so a portable client needs per-provider adapters"
|
|
],
|
|
"correct": 3,
|
|
"explanation": ""
|
|
},
|
|
{
|
|
"stage": "post",
|
|
"question": "Per the lesson, what is the simplest decision rule for triaging a workload to batch?",
|
|
"options": [
|
|
"If the prompt is under 1k tokens, batch it",
|
|
"If it uses tools, batch it",
|
|
"Batch only when the gateway requires it",
|
|
"If the user wouldn't notice a 24-hour delivery, always batch (and stack caching)"
|
|
],
|
|
"correct": 3,
|
|
"explanation": ""
|
|
}
|
|
]
|
|
}
|