部分 API 端點預設會以串流方式傳送回應,例如 /api/generate。這些回應是以換行分隔的 JSON 格式(即 application/x-ndjson 內容類型)提供的。例如:
json
{"model":"gemma4","created_at":"2025-10-26T17:15:24.097767Z","response":"That","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.109172Z","response":"'","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.121485Z","response":"s","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.132802Z","response":" a","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.143931Z","response":" fantastic","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.155176Z","response":" question","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"!","done":true, "done_reason": "stop"}關閉串流
對於支援串流的任何端點,可以在請求主體中提供 {"stream": false} 來關閉串流。這將使回應改以 application/json 格式回傳:
json
{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"That's a fantastic question!","done":true}何時使用串流與非串流
串流 (預設):
- 即時回應生成
- 較低的感知延遲
- 適合長文本生成
非串流:
- 處理更簡單
- 適合簡短回應或結構化輸出
- 在某些應用程式中較易於處理