14 lines
511 B
TOML
14 lines
511 B
TOML
[POST]
|
|
summary = "模拟 AI 流式对话（SSE，逐 token 输出）"
|
|
docstring = "流式端点示例：@rpc_method 返回生成器，框架逐块多回复推送，网关以 text/event-stream 转发。curl -N 可观察逐块到达。"
|
|
auth_required = false
|
|
stream = true
|
|
# 流式超时模型: timeout = 流总寿命上限（zenoh query deadline），
|
|
# stream_idle_timeout = 网关侧连续无数据块的最大间隔
|
|
timeout = 300.0
|
|
stream_idle_timeout = 10.0
|
|
params = [
|
|
"prompt: str",
|
|
"tokens: int"
|
|
]
|