Status
GET/status
Status
Returns all information about the app and its current status. More verbose than the /status endpoint on the inference endpoint and exposes more sensitive information about the deployment which only the admin should have access to.
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.
Responses​
- 200
- 503
Server is running, backend configuration is returned in body
- application/json
- Schema
- Example (from schema)
Schema
config
object
required
The app configuration
Default value: 2097152
Default value: true
Default value: 1
Default value: 3005
Default value: 3001
Default value: 150000
Default value: 1000
Default value: 3003
Default value: 3000
Default value: 500
Default value: /path/to/home/artefacts
Default value: primary
Default value: 3004
Default value: 3002
status
object
nullable
dead_readers
object
required
property name*
ReaderInfo
last_heartbeat
object
required
property name*
LastHeartbeat
live_readers
object
required
property name*
ReaderInfo
loading_readers
object
required
property name*
ReaderInfo
{
"config": {
"allow_remote_images": false,
"body_size_limit_bytes": 2097152,
"echo": false,
"enable_metrics": true,
"heartbeat_check_interval": 1,
"internal_port": 3005,
"management_port": 3001,
"max_prompt_string_bytes": 150000,
"max_user_batch_size": 1000,
"openai_port": 3003,
"port": 3000,
"reader_message_timeout_ms": 500,
"repository_path": "/path/to/home/artefacts",
"reserved_consumers": "primary",
"snowflake_port": 3004,
"vertex_port": 3002
},
"status": {
"dead_readers": {},
"last_heartbeat": {},
"live_readers": {},
"loading_readers": {},
"reserved_consumers": [
"string"
]
}
}
Server is not available