Status

GET 
/status

Status

Returns all information about the app and its current status.

The /status endpoint gives information about currently active models, and the config the app is running with. A 200 response indicates that the server is running. To check if the server is ready to receive requests, see the /healthz endpoint.

Request

Responses

200

Server is running, backend configuration is returned in body

application/json

Schema

Schema

config

object

required

The app configuration

batch_duration_millis int64required

Default value: 100

echo booleanrequired

Default value: false

enable_metrics booleanrequired

Default value: true

heartbeat_check_interval int64required

Default value: 1

launch_management_server booleanrequired

Default value: true

launch_sagemaker_server booleanrequired

Default value: true

launch_vertex_server booleanrequired

Default value: true

management_port int32required

Default value: 3001

max_batch_size integerrequired

Default value: 8

port int32required

Default value: 3000

vertex_port int32required

Default value: 3002

status

object

nullable

dead_readers

object

required

property name*

ReaderInfo

backend stringrequired

consumer_group stringrequired

model_name stringrequired

model_type stringrequired

pids int32[]required

input_model_paths

object

required

property name* string

last_heartbeat

object

required

property name*

LastHeartbeat

heartbeat_timestamp int64required

heartbeat_wait_interval int64required

live_readers

object

required

property name*

ReaderInfo

backend stringrequired

consumer_group stringrequired

model_name stringrequired

model_type stringrequired

pids int32[]required

loading_readers

object

required

property name*

ReaderInfo

backend stringrequired

consumer_group stringrequired

model_name stringrequired

model_type stringrequired

pids int32[]required

Example (from schema)

{
  "config": {
    "batch_duration_millis": 100,
    "echo": false,
    "enable_metrics": true,
    "heartbeat_check_interval": 1,
    "launch_management_server": true,
    "launch_sagemaker_server": true,
    "launch_vertex_server": true,
    "management_port": 3001,
    "max_batch_size": 8,
    "port": 3000,
    "vertex_port": 3002
  },
  "status": {
    "dead_readers": {},
    "input_model_paths": {},
    "last_heartbeat": {},
    "live_readers": {},
    "loading_readers": {}
  }
}

503

Server is not available

Loading...