Saltar al contenido principal
GET
/
api
/
v1
/
serving
/
deployments
/
{deployment_id}
/
metrics
Python (SDK)
from meetkai_mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.serving.deployments.get_metrics(deployment_id="<id>")

    # Handle response
    print(res)
{
  "replicas": 123,
  "queue_backlog": 123,
  "accelerator_utilization": 123,
  "accelerator_memory_used_mb": 123,
  "requests_per_second": 123
}

Autorizaciones

Authorization
string
header
requerido

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Encabezados

X-On-Behalf-Of
string

Optional external end-user identifier forwarded by the API gateway.

Parámetros de ruta

deployment_id
string
requerido

Respuesta

Respuesta Exitosa

Métricas en vivo de servicio para un despliegue.

replicas
integer
requerido
queue_backlog
integer
requerido

Solicitudes en espera de una réplica libre

accelerator_utilization
number
requerido

0,0–1,0 entre réplicas

accelerator_memory_used_mb
integer
requerido
requests_per_second
number
requerido