GetCServeV3DeploymentResponse.md

GetCServeV3DeploymentResponse

Properties

Name	Type	Description	Notes
creator_email	str
cluster_id	int
id	int
name	str
endpoint_url	str
image_url	str		[optional]
type	DeploymentType
status	DeploymentStatus
created_at	datetime
hardware_instance_id	int
revision_number	int
user_annotations	Dict[str, str]		[optional]
recipe	CServeV2Recipe
cserve_version	str		[optional]
min_replicas	int
max_replicas	int
initial_replicas	int		[optional]
endpoint_certificate_authority	str		[optional]
endpoint_bearer_token	str		[optional]
concurrency	int		[optional]
cooldown_period	int		[optional] [default to 1800]
env_vars	Dict[str, str]		[optional]
enable_logging	bool		[optional] [default to True]
enable_node_model_cache	bool		[optional] [default to False]
session_affinity	bool	Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.	[optional] [default to False]

Example

from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse

# TODO update the JSON string below
json = "{}"
# create an instance of GetCServeV3DeploymentResponse from a JSON string
get_c_serve_v3_deployment_response_instance = GetCServeV3DeploymentResponse.from_json(json)
# print the JSON string representation of the object
print(GetCServeV3DeploymentResponse.to_json())

# convert the object into a dict
get_c_serve_v3_deployment_response_dict = get_c_serve_v3_deployment_response_instance.to_dict()
# create an instance of GetCServeV3DeploymentResponse from a dict
get_c_serve_v3_deployment_response_from_dict = GetCServeV3DeploymentResponse.from_dict(get_c_serve_v3_deployment_response_dict)

[Back to Model list] [Back to API list] [Back to README]