gcore 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

gcore/types/cloud/inference/inference_deployment.py

@@ -0,0 +1,266 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Optional
+from typing_extensions import Literal
+
+from ..logging import Logging
+from ...._models import BaseModel
+from .probe_config import ProbeConfig
+
+__all__ = [
+    "InferenceDeployment",
+    "Container",
+    "ContainerDeployStatus",
+    "ContainerScale",
+    "ContainerScaleTriggers",
+    "ContainerScaleTriggersCPU",
+    "ContainerScaleTriggersGPUMemory",
+    "ContainerScaleTriggersGPUUtilization",
+    "ContainerScaleTriggersHTTP",
+    "ContainerScaleTriggersMemory",
+    "ContainerScaleTriggersSqs",
+    "IngressOpts",
+    "ObjectReference",
+    "Probes",
+]
+
+
+class ContainerDeployStatus(BaseModel):
+    ready: int
+    """Number of ready instances"""
+
+    total: int
+    """Total number of instances"""
+
+
+class ContainerScaleTriggersCPU(BaseModel):
+    threshold: int
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUMemory(BaseModel):
+    threshold: int
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUUtilization(BaseModel):
+    threshold: int
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersHTTP(BaseModel):
+    rate: int
+    """Request count per 'window' seconds for the http trigger"""
+
+    window: int
+    """Time window for rate calculation in seconds"""
+
+
+class ContainerScaleTriggersMemory(BaseModel):
+    threshold: int
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersSqs(BaseModel):
+    activation_queue_length: int
+    """Number of messages for activation"""
+
+    aws_endpoint: Optional[str] = None
+    """Custom AWS endpoint"""
+
+    aws_region: str
+    """AWS region"""
+
+    queue_length: int
+    """Number of messages for one replica"""
+
+    queue_url: str
+    """SQS queue URL"""
+
+    scale_on_delayed: bool
+    """Scale on delayed messages"""
+
+    scale_on_flight: bool
+    """Scale on in-flight messages"""
+
+    secret_name: str
+    """Auth secret name"""
+
+
+class ContainerScaleTriggers(BaseModel):
+    cpu: Optional[ContainerScaleTriggersCPU] = None
+    """CPU trigger configuration"""
+
+    gpu_memory: Optional[ContainerScaleTriggersGPUMemory] = None
+    """GPU memory trigger configuration.
+
+    Calculated by `DCGM_FI_DEV_MEM_COPY_UTIL` metric
+    """
+
+    gpu_utilization: Optional[ContainerScaleTriggersGPUUtilization] = None
+    """GPU utilization trigger configuration.
+
+    Calculated by `DCGM_FI_DEV_GPU_UTIL` metric
+    """
+
+    http: Optional[ContainerScaleTriggersHTTP] = None
+    """HTTP trigger configuration"""
+
+    memory: Optional[ContainerScaleTriggersMemory] = None
+    """Memory trigger configuration"""
+
+    sqs: Optional[ContainerScaleTriggersSqs] = None
+    """SQS trigger configuration"""
+
+
+class ContainerScale(BaseModel):
+    cooldown_period: Optional[int] = None
+    """Cooldown period between scaling actions in seconds"""
+
+    max: int
+    """Maximum scale for the container"""
+
+    min: int
+    """Minimum scale for the container"""
+
+    polling_interval: Optional[int] = None
+    """Polling interval for scaling triggers in seconds"""
+
+    triggers: ContainerScaleTriggers
+    """Triggers for scaling actions"""
+
+
+class Container(BaseModel):
+    address: Optional[str] = None
+    """Address of the inference instance"""
+
+    deploy_status: ContainerDeployStatus
+    """Status of the containers deployment"""
+
+    error_message: Optional[str] = None
+    """Error message if the container deployment failed"""
+
+    region_id: int
+    """Region name for the container"""
+
+    scale: ContainerScale
+    """Scale for the container"""
+
+
+class IngressOpts(BaseModel):
+    disable_response_buffering: bool
+    """Disable response buffering if true.
+
+    A client usually has a much slower connection and can not consume the response
+    data as fast as it is produced by an upstream application. Ingress tries to
+    buffer the whole response in order to release the upstream application as soon
+    as possible.By default, the response buffering is enabled.
+    """
+
+
+class ObjectReference(BaseModel):
+    kind: Literal["AppDeployment"]
+    """Kind of the inference object to be referenced"""
+
+    name: str
+    """Name of the inference object to be referenced"""
+
+
+class Probes(BaseModel):
+    liveness_probe: Optional[ProbeConfig] = None
+    """Liveness probe configuration"""
+
+    readiness_probe: Optional[ProbeConfig] = None
+    """Readiness probe configuration"""
+
+    startup_probe: Optional[ProbeConfig] = None
+    """Startup probe configuration"""
+
+
+class InferenceDeployment(BaseModel):
+    address: Optional[str] = None
+    """Address of the inference instance"""
+
+    auth_enabled: bool
+    """`true` if instance uses API key authentication.
+
+    `"Authorization": "Bearer ****\\**"` or `"X-Api-Key": "****\\**"` header is required
+    for the requests to the instance if enabled.
+    """
+
+    command: Optional[str] = None
+    """Command to be executed when running a container from an image."""
+
+    containers: List[Container]
+    """List of containers for the inference instance"""
+
+    created_at: Optional[str] = None
+    """Inference instance creation date in ISO 8601 format."""
+
+    credentials_name: str
+    """Registry credentials name"""
+
+    description: str
+    """Inference instance description."""
+
+    envs: Optional[Dict[str, str]] = None
+    """Environment variables for the inference instance"""
+
+    flavor_name: str
+    """Flavor name for the inference instance"""
+
+    image: str
+    """Docker image for the inference instance.
+
+    This field should contain the image name and tag in the format 'name:tag', e.g.,
+    'nginx:latest'. It defaults to Docker Hub as the image registry, but any
+    accessible Docker image URL can be specified.
+    """
+
+    ingress_opts: Optional[IngressOpts] = None
+    """Ingress options for the inference instance"""
+
+    listening_port: int
+    """Listening port for the inference instance."""
+
+    logging: Optional[Logging] = None
+    """Logging configuration for the inference instance"""
+
+    name: str
+    """Inference instance name."""
+
+    object_references: List[ObjectReference]
+    """Indicates to which parent object this inference belongs to."""
+
+    probes: Optional[Probes] = None
+    """Probes configured for all containers of the inference instance."""
+
+    project_id: int
+    """Project ID. If not provided, your default project ID will be used."""
+
+    status: Literal["ACTIVE", "DELETING", "DEPLOYING", "DISABLED", "PARTIALLYDEPLOYED", "PENDING"]
+    """Inference instance status. Value can be one of the following:
+
+    - `DEPLOYING` - The instance is being deployed. Containers are not yet created.
+    - `PARTIALLYDEPLOYED` - All containers have been created, but some may not be
+      ready yet. Instances stuck in this state typically indicate either image being
+      pulled, or a failure of some kind. In the latter case, the `error_message`
+      field of the respective container object in the `containers` collection
+      explains the failure reason.
+    - `ACTIVE` - The instance is running and ready to accept requests.
+    - `DISABLED` - The instance is disabled and not accepting any requests.
+    - `PENDING` - The instance is running but scaled to zero. It will be
+      automatically scaled up when a request is made.
+    - `DELETING` - The instance is being deleted.
+    """
+
+    timeout: Optional[int] = None
+    """
+    Specifies the duration in seconds without any requests after which the
+    containers will be downscaled to their minimum scale value as defined by
+    `scale.min`. If set, this helps in optimizing resource usage by reducing the
+    number of container instances during periods of inactivity.
+    """
+
+    api_keys: Optional[List[str]] = None
+    """List of API keys for the inference instance"""

gcore/types/cloud/inference/{inference_apikey_secret.py → inference_deployment_api_key.py}

@@ -4,10 +4,10 @@ from typing_extensions import Literal
 
 from ...._models import BaseModel
 
-__all__ = ["InferenceApikeySecret"]
+__all__ = ["InferenceDeploymentAPIKey"]
 
 
-class InferenceApikeySecret(BaseModel):
+class InferenceDeploymentAPIKey(BaseModel):
     secret: str
     """API key secret"""
 

gcore/types/cloud/inference/{mlcatalog_model_card.py → inference_model.py}

@@ -6,10 +6,10 @@ from pydantic import Field as FieldInfo
 
 from ...._models import BaseModel
 
-__all__ = ["MlcatalogModelCard"]
+__all__ = ["InferenceModel"]
 
 
-class MlcatalogModelCard(BaseModel):
+class InferenceModel(BaseModel):
     id: str
     """Model ID."""
 

gcore/types/cloud/inference/{inference_registry_credential.py → inference_registry_credentials.py}

@@ -2,10 +2,10 @@
 
 from ...._models import BaseModel
 
-__all__ = ["InferenceRegistryCredential"]
+__all__ = ["InferenceRegistryCredentials"]
 
 
-class InferenceRegistryCredential(BaseModel):
+class InferenceRegistryCredentials(BaseModel):
     name: str
     """Registry credential name."""
 

gcore/types/cloud/inference/{inference_registry_credential_full.py → inference_registry_credentials_create.py}

@@ -2,10 +2,10 @@
 
 from ...._models import BaseModel
 
-__all__ = ["InferenceRegistryCredentialFull"]
+__all__ = ["InferenceRegistryCredentialsCreate"]
 
 
-class InferenceRegistryCredentialFull(BaseModel):
+class InferenceRegistryCredentialsCreate(BaseModel):
     name: str
     """Registry credential name."""
 

gcore/types/cloud/inference/inference_secret.py

@@ -1,13 +1,20 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 from ...._models import BaseModel
-from ..aws_iam_data import AwsIamData
 
-__all__ = ["InferenceSecret"]
+__all__ = ["InferenceSecret", "Data"]
+
+
+class Data(BaseModel):
+    aws_access_key_id: str
+    """AWS IAM key ID."""
+
+    aws_secret_access_key: str
+    """AWS IAM secret key."""
 
 
 class InferenceSecret(BaseModel):
-    data: AwsIamData
+    data: Data
     """Secret data."""
 
     name: str

gcore/types/cloud/inference/model_list_params.py

@@ -2,9 +2,7 @@
 
 from __future__ import annotations
 
-from typing_extensions import TypedDict
-
-from .mlcatalog_order_by_choices import MlcatalogOrderByChoices
+from typing_extensions import Literal, TypedDict
 
 __all__ = ["ModelListParams"]
 
@@ -19,5 +17,5 @@ class ModelListParams(TypedDict, total=False):
     Offset value is used to exclude the first set of records from the result
     """
 
-    order_by: MlcatalogOrderByChoices
+    order_by: Literal["name.asc", "name.desc"]
     """Order instances by transmitted fields and directions"""

gcore/types/cloud/{container_probe.py → inference/probe.py}

@@ -2,22 +2,22 @@
 
 from typing import Optional
 
-from ..._models import BaseModel
-from .container_probe_exec import ContainerProbeExec
-from .container_probe_http_get import ContainerProbeHTTPGet
-from .container_probe_tcp_socket import ContainerProbeTcpSocket
+from ...._models import BaseModel
+from .probe_exec import ProbeExec
+from .probe_http_get import ProbeHTTPGet
+from .probe_tcp_socket import ProbeTcpSocket
 
-__all__ = ["ContainerProbe"]
+__all__ = ["Probe"]
 
 
-class ContainerProbe(BaseModel):
-    exec: Optional[ContainerProbeExec] = None
+class Probe(BaseModel):
+    exec: Optional[ProbeExec] = None
     """Exec probe configuration"""
 
     failure_threshold: int
     """The number of consecutive probe failures that mark the container as unhealthy."""
 
-    http_get: Optional[ContainerProbeHTTPGet] = None
+    http_get: Optional[ProbeHTTPGet] = None
     """HTTP GET probe configuration"""
 
     initial_delay_seconds: int
@@ -29,7 +29,7 @@ class ContainerProbe(BaseModel):
     success_threshold: int
     """The number of consecutive successful probes that mark the container as healthy."""
 
-    tcp_socket: Optional[ContainerProbeTcpSocket] = None
+    tcp_socket: Optional[ProbeTcpSocket] = None
     """TCP socket probe configuration"""
 
     timeout_seconds: int

gcore/types/cloud/{container_probe_config.py → inference/probe_config.py}

@@ -2,15 +2,15 @@
 
 from typing import Optional
 
-from ..._models import BaseModel
-from .container_probe import ContainerProbe
+from .probe import Probe
+from ...._models import BaseModel
 
-__all__ = ["ContainerProbeConfig"]
+__all__ = ["ProbeConfig"]
 
 
-class ContainerProbeConfig(BaseModel):
+class ProbeConfig(BaseModel):
     enabled: bool
     """Whether the probe is enabled or not."""
 
-    probe: Optional[ContainerProbe] = None
+    probe: Optional[Probe] = None
     """Probe configuration (exec, `http_get` or `tcp_socket`)"""

gcore/types/cloud/{container_probe_exec.py → inference/probe_exec.py}

@@ -2,11 +2,11 @@
 
 from typing import List
 
-from ..._models import BaseModel
+from ...._models import BaseModel
 
-__all__ = ["ContainerProbeExec"]
+__all__ = ["ProbeExec"]
 
 
-class ContainerProbeExec(BaseModel):
+class ProbeExec(BaseModel):
     command: List[str]
     """Command to be executed inside the running container."""

gcore/types/cloud/{container_probe_http_get.py → inference/probe_http_get.py}

@@ -4,12 +4,12 @@ from typing import Dict, Optional
 
 from pydantic import Field as FieldInfo
 
-from ..._models import BaseModel
+from ...._models import BaseModel
 
-__all__ = ["ContainerProbeHTTPGet"]
+__all__ = ["ProbeHTTPGet"]
 
 
-class ContainerProbeHTTPGet(BaseModel):
+class ProbeHTTPGet(BaseModel):
     headers: Dict[str, str]
     """HTTP headers to be sent with the request."""
 

gcore/types/cloud/{container_probe_tcp_socket.py → inference/probe_tcp_socket.py}

@@ -1,10 +1,10 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-from ..._models import BaseModel
+from ...._models import BaseModel
 
-__all__ = ["ContainerProbeTcpSocket"]
+__all__ = ["ProbeTcpSocket"]
 
 
-class ContainerProbeTcpSocket(BaseModel):
+class ProbeTcpSocket(BaseModel):
     port: int
     """Port number to check if it's open."""

gcore/types/cloud/inference/secret_create_params.py

@@ -4,16 +4,14 @@ from __future__ import annotations
 
 from typing_extensions import Required, TypedDict
 
-from ..aws_iam_data_param import AwsIamDataParam
-
-__all__ = ["SecretCreateParams"]
+__all__ = ["SecretCreateParams", "Data"]
 
 
 class SecretCreateParams(TypedDict, total=False):
     project_id: int
     """Project ID"""
 
-    data: Required[AwsIamDataParam]
+    data: Required[Data]
     """Secret data."""
 
     name: Required[str]
@@ -21,3 +19,11 @@ class SecretCreateParams(TypedDict, total=False):
 
     type: Required[str]
     """Secret type. Currently only `aws-iam` is supported."""
+
+
+class Data(TypedDict, total=False):
+    aws_access_key_id: Required[str]
+    """AWS IAM key ID."""
+
+    aws_secret_access_key: Required[str]
+    """AWS IAM secret key."""

gcore/types/cloud/inference/secret_replace_params.py

@@ -4,17 +4,23 @@ from __future__ import annotations
 
 from typing_extensions import Required, TypedDict
 
-from ..aws_iam_data_param import AwsIamDataParam
-
-__all__ = ["SecretReplaceParams"]
+__all__ = ["SecretReplaceParams", "Data"]
 
 
 class SecretReplaceParams(TypedDict, total=False):
     project_id: int
     """Project ID"""
 
-    data: Required[AwsIamDataParam]
+    data: Required[Data]
     """Secret data."""
 
     type: Required[str]
     """Secret type."""
+
+
+class Data(TypedDict, total=False):
+    aws_access_key_id: Required[str]
+    """AWS IAM key ID."""
+
+    aws_secret_access_key: Required[str]
+    """AWS IAM secret key."""

gcore/types/cloud/{region_capacity.py → inference_region_capacity.py}

@@ -2,13 +2,20 @@
 
 from typing import List
 
-from .capacity import Capacity
 from ..._models import BaseModel
 
-__all__ = ["RegionCapacity"]
+__all__ = ["InferenceRegionCapacity", "Capacity"]
 
 
-class RegionCapacity(BaseModel):
+class Capacity(BaseModel):
+    capacity: int
+    """Available capacity."""
+
+    flavor_name: str
+    """Flavor name."""
+
+
+class InferenceRegionCapacity(BaseModel):
     capacity: List[Capacity]
     """List of capacities by flavor."""
 

gcore/types/cloud/{region_capacity_list.py → inference_region_capacity_list.py}

@@ -3,14 +3,14 @@
 from typing import List
 
 from ..._models import BaseModel
-from .region_capacity import RegionCapacity
+from .inference_region_capacity import InferenceRegionCapacity
 
-__all__ = ["RegionCapacityList"]
+__all__ = ["InferenceRegionCapacityList"]
 
 
-class RegionCapacityList(BaseModel):
+class InferenceRegionCapacityList(BaseModel):
     count: int
     """Number of objects"""
 
-    results: List[RegionCapacity]
+    results: List[InferenceRegionCapacity]
     """Objects"""

gcore/types/cloud/instance_create_params.py

@@ -109,7 +109,7 @@ class InstanceCreateParams(TypedDict, total=False):
     ssh_key_name: Optional[str]
     """
     Specifies the name of the SSH keypair, created via the
-    [/v1/`ssh_keys` endpoint](/docs/api-reference/ssh-keys/add-or-generate-ssh-key).
+    [/v1/`ssh_keys` endpoint](/docs/api-reference/cloud/ssh-keys/add-or-generate-ssh-key).
     """
 
     tags: Dict[str, str]

gcore/types/cloud/task_list_params.py

@@ -65,7 +65,8 @@ class TaskListParams(TypedDict, total=False):
     '`create_ai_cluster_gpu`', '`create_bm`', '`create_caas_container`',
     '`create_dbaas_postgres_cluster`', '`create_ddos_profile`',
     '`create_faas_function`', '`create_faas_namespace`', '`create_fip`',
-    '`create_gpu_virtual_cluster`', '`create_image`', '`create_inference_instance`',
+    '`create_gpu_virtual_cluster`', '`create_image`',
+    '`create_inference_application`', '`create_inference_instance`',
     '`create_inference_instance_key`', '`create_k8s_cluster_pool_v2`',
     '`create_k8s_cluster_v2`', '`create_l7policy`', '`create_l7rule`',
     '`create_lblistener`', '`create_lbmember`', '`create_lbpool`',
@@ -77,14 +78,14 @@ class TaskListParams(TypedDict, total=False):
     '`delete_dbaas_postgres_cluster`', '`delete_ddos_profile`',
     '`delete_faas_function`', '`delete_faas_namespace`', '`delete_fip`',
     '`delete_gpu_virtual_cluster`', '`delete_gpu_virtual_server`', '`delete_image`',
-    '`delete_inference_instance`', '`delete_k8s_cluster_pool_v2`',
-    '`delete_k8s_cluster_v2`', '`delete_l7policy`', '`delete_l7rule`',
-    '`delete_lblistener`', '`delete_lbmember`', '`delete_lbmetadata`',
-    '`delete_lbpool`', '`delete_loadbalancer`', '`delete_network`',
-    '`delete_reserved_fixed_ip`', '`delete_router`', '`delete_secret`',
-    '`delete_servergroup`', '`delete_sfs`', '`delete_snapshot`', '`delete_subnet`',
-    '`delete_vm`', '`delete_volume`', '`detach_vm_interface`', '`detach_volume`',
-    '`download_image`', '`downscale_ai_cluster_gpu`',
+    '`delete_inference_application`', '`delete_inference_instance`',
+    '`delete_k8s_cluster_pool_v2`', '`delete_k8s_cluster_v2`', '`delete_l7policy`',
+    '`delete_l7rule`', '`delete_lblistener`', '`delete_lbmember`',
+    '`delete_lbmetadata`', '`delete_lbpool`', '`delete_loadbalancer`',
+    '`delete_network`', '`delete_reserved_fixed_ip`', '`delete_router`',
+    '`delete_secret`', '`delete_servergroup`', '`delete_sfs`', '`delete_snapshot`',
+    '`delete_subnet`', '`delete_vm`', '`delete_volume`', '`detach_vm_interface`',
+    '`detach_volume`', '`download_image`', '`downscale_ai_cluster_gpu`',
     '`downscale_gpu_virtual_cluster`', '`extend_sfs`', '`extend_volume`',
     '`failover_loadbalancer`', '`hard_reboot_gpu_baremetal_server`',
     '`hard_reboot_gpu_virtual_cluster`', '`hard_reboot_gpu_virtual_server`',
@@ -100,11 +101,11 @@ class TaskListParams(TypedDict, total=False):
     '`start_gpu_virtual_server`', '`start_vm`', '`stop_gpu_baremetal_server`',
     '`stop_gpu_virtual_cluster`', '`stop_gpu_virtual_server`', '`stop_vm`',
     '`suspend_vm`', '`sync_private_flavors`', '`update_ddos_profile`',
-    '`update_inference_instance`', '`update_inference_instance_key`',
-    '`update_k8s_cluster_v2`', '`update_lbmetadata`',
-    '`update_port_allowed_address_pairs`', '`update_tags_gpu_virtual_cluster`',
-    '`upgrade_k8s_cluster_v2`', '`upscale_ai_cluster_gpu`',
-    '`upscale_gpu_virtual_cluster`']
+    '`update_inference_application`', '`update_inference_instance`',
+    '`update_inference_instance_key`', '`update_k8s_cluster_v2`',
+    '`update_lbmetadata`', '`update_port_allowed_address_pairs`',
+    '`update_tags_gpu_virtual_cluster`', '`upgrade_k8s_cluster_v2`',
+    '`upscale_ai_cluster_gpu`', '`upscale_gpu_virtual_cluster`']
     """
 
     to_timestamp: Annotated[Union[str, datetime, None], PropertyInfo(format="iso8601")]