gcore 0.1.0a1__py3-none-any.whl

gcore/types/cloud/inference/deployment_create_params.py

@@ -0,0 +1,222 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Iterable, Optional
+from typing_extensions import Required, Annotated, TypedDict
+
+from ...._utils import PropertyInfo
+from ..ingress_opts_param import IngressOptsParam
+from ..laas_index_retention_policy_param import LaasIndexRetentionPolicyParam
+from ..container_probe_config_create_param import ContainerProbeConfigCreateParam
+
+__all__ = [
+    "DeploymentCreateParams",
+    "Container",
+    "ContainerScale",
+    "ContainerScaleTriggers",
+    "ContainerScaleTriggersCPU",
+    "ContainerScaleTriggersGPUMemory",
+    "ContainerScaleTriggersGPUUtilization",
+    "ContainerScaleTriggersHTTP",
+    "ContainerScaleTriggersMemory",
+    "ContainerScaleTriggersSqs",
+    "Logging",
+    "Probes",
+]
+
+
+class DeploymentCreateParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    containers: Required[Iterable[Container]]
+    """List of containers for the inference instance."""
+
+    flavor_name: Required[str]
+    """Flavor name for the inference instance."""
+
+    image: Required[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.
+    """
+
+    listening_port: Required[int]
+    """Listening port for the inference instance."""
+
+    name: Required[str]
+    """Inference instance name."""
+
+    auth_enabled: bool
+    """Set to `true` to enable API key authentication for the inference instance.
+
+    `"Authorization": "Bearer *****"` or `"X-Api-Key": "*****"` header is required
+    for the requests to the instance if enabled
+    """
+
+    command: Optional[List[str]]
+    """Command to be executed when running a container from an image."""
+
+    credentials_name: Optional[str]
+    """Registry credentials name"""
+
+    description: Optional[str]
+    """Inference instance description."""
+
+    envs: Dict[str, str]
+    """Environment variables for the inference instance."""
+
+    ingress_opts: Optional[IngressOptsParam]
+    """Ingress options for the inference instance"""
+
+    logging: Optional[Logging]
+    """Logging configuration for the inference instance"""
+
+    probes: Optional[Probes]
+    """Probes configured for all containers of the inference instance.
+
+    If probes are not provided, and the image_name is from a the Model Catalog
+    registry, the default probes will be used.
+    """
+
+    api_timeout: Annotated[Optional[int], PropertyInfo(alias="timeout")]
+    """
+    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. The default value
+    when the parameter is not set is 120.
+    """
+
+
+class ContainerScaleTriggersCPU(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUMemory(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUUtilization(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersHTTP(TypedDict, total=False):
+    rate: Required[int]
+    """Request count per 'window' seconds for the http trigger"""
+
+    window: Required[int]
+    """Time window for rate calculation in seconds"""
+
+
+class ContainerScaleTriggersMemory(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersSqs(TypedDict, total=False):
+    activation_queue_length: Required[int]
+    """Number of messages for activation"""
+
+    aws_region: Required[str]
+    """AWS region"""
+
+    queue_length: Required[int]
+    """Number of messages for one replica"""
+
+    queue_url: Required[str]
+    """SQS queue URL"""
+
+    secret_name: Required[str]
+    """Auth secret name"""
+
+    aws_endpoint: Optional[str]
+    """Custom AWS endpoint"""
+
+    scale_on_delayed: bool
+    """Scale on delayed messages"""
+
+    scale_on_flight: bool
+    """Scale on in-flight messages"""
+
+
+class ContainerScaleTriggers(TypedDict, total=False):
+    cpu: Optional[ContainerScaleTriggersCPU]
+    """CPU trigger configuration"""
+
+    gpu_memory: Optional[ContainerScaleTriggersGPUMemory]
+    """GPU memory trigger configuration.
+
+    Calculated by DCGM_FI_DEV_MEM_COPY_UTIL metric
+    """
+
+    gpu_utilization: Optional[ContainerScaleTriggersGPUUtilization]
+    """GPU utilization trigger configuration.
+
+    Calculated by DCGM_FI_DEV_GPU_UTIL metric
+    """
+
+    http: Optional[ContainerScaleTriggersHTTP]
+    """HTTP trigger configuration"""
+
+    memory: Optional[ContainerScaleTriggersMemory]
+    """Memory trigger configuration"""
+
+    sqs: Optional[ContainerScaleTriggersSqs]
+    """SQS trigger configuration"""
+
+
+class ContainerScale(TypedDict, total=False):
+    max: Required[int]
+    """Maximum scale for the container"""
+
+    min: Required[int]
+    """Minimum scale for the container"""
+
+    cooldown_period: Optional[int]
+    """Cooldown period between scaling actions in seconds"""
+
+    polling_interval: Optional[int]
+    """Polling interval for scaling triggers in seconds"""
+
+    triggers: ContainerScaleTriggers
+    """Triggers for scaling actions"""
+
+
+class Container(TypedDict, total=False):
+    region_id: Required[int]
+    """Region id for the container"""
+
+    scale: Required[ContainerScale]
+    """Scale for the container"""
+
+
+class Logging(TypedDict, total=False):
+    destination_region_id: Optional[int]
+    """ID of the region in which the logs will be stored"""
+
+    enabled: bool
+    """Enable or disable log streaming"""
+
+    retention_policy: Optional[LaasIndexRetentionPolicyParam]
+    """Logs retention policy"""
+
+    topic_name: Optional[str]
+    """The topic name to stream logs to"""
+
+
+class Probes(TypedDict, total=False):
+    liveness_probe: Optional[ContainerProbeConfigCreateParam]
+    """Liveness probe configuration"""
+
+    readiness_probe: Optional[ContainerProbeConfigCreateParam]
+    """Readiness probe configuration"""
+
+    startup_probe: Optional[ContainerProbeConfigCreateParam]
+    """Startup probe configuration"""

gcore/types/cloud/inference/deployment_list_params.py

@@ -0,0 +1,21 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import TypedDict
+
+__all__ = ["DeploymentListParams"]
+
+
+class DeploymentListParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    limit: int
+    """Optional. Limit the number of returned items"""
+
+    offset: int
+    """Optional.
+
+    Offset value is used to exclude the first set of records from the result
+    """

gcore/types/cloud/inference/deployment_update_params.py

@@ -0,0 +1,215 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Iterable, Optional
+from typing_extensions import Required, Annotated, TypedDict
+
+from ...._utils import PropertyInfo
+from ..ingress_opts_param import IngressOptsParam
+from ..laas_index_retention_policy_param import LaasIndexRetentionPolicyParam
+from ..container_probe_config_create_param import ContainerProbeConfigCreateParam
+
+__all__ = [
+    "DeploymentUpdateParams",
+    "Container",
+    "ContainerScale",
+    "ContainerScaleTriggers",
+    "ContainerScaleTriggersCPU",
+    "ContainerScaleTriggersGPUMemory",
+    "ContainerScaleTriggersGPUUtilization",
+    "ContainerScaleTriggersHTTP",
+    "ContainerScaleTriggersMemory",
+    "ContainerScaleTriggersSqs",
+    "Logging",
+    "Probes",
+]
+
+
+class DeploymentUpdateParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    auth_enabled: Optional[bool]
+    """Set to `true` to enable API key authentication for the inference instance.
+
+    `"Authorization": "Bearer *****"` or `"X-Api-Key": "*****"` header is required
+    for the requests to the instance if enabled
+    """
+
+    command: Optional[List[str]]
+    """Command to be executed when running a container from an image."""
+
+    containers: Optional[Iterable[Container]]
+    """List of containers for the inference instance."""
+
+    credentials_name: Optional[str]
+    """Registry credentials name"""
+
+    description: Optional[str]
+    """Inference instance description."""
+
+    envs: Optional[Dict[str, str]]
+    """Environment variables for the inference instance."""
+
+    flavor_name: Optional[str]
+    """Flavor name for the inference instance."""
+
+    image: Optional[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[IngressOptsParam]
+    """Ingress options for the inference instance"""
+
+    listening_port: Optional[int]
+    """Listening port for the inference instance."""
+
+    logging: Optional[Logging]
+    """Logging configuration for the inference instance"""
+
+    probes: Optional[Probes]
+    """Probes configured for all containers of the inference instance."""
+
+    api_timeout: Annotated[Optional[int], PropertyInfo(alias="timeout")]
+    """
+    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. The default value
+    when the parameter is not set is 120.
+    """
+
+
+class ContainerScaleTriggersCPU(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUMemory(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersGPUUtilization(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersHTTP(TypedDict, total=False):
+    rate: Required[int]
+    """Request count per 'window' seconds for the http trigger"""
+
+    window: Required[int]
+    """Time window for rate calculation in seconds"""
+
+
+class ContainerScaleTriggersMemory(TypedDict, total=False):
+    threshold: Required[int]
+    """Threshold value for the trigger in percentage"""
+
+
+class ContainerScaleTriggersSqs(TypedDict, total=False):
+    activation_queue_length: Required[int]
+    """Number of messages for activation"""
+
+    aws_region: Required[str]
+    """AWS region"""
+
+    queue_length: Required[int]
+    """Number of messages for one replica"""
+
+    queue_url: Required[str]
+    """SQS queue URL"""
+
+    secret_name: Required[str]
+    """Auth secret name"""
+
+    aws_endpoint: Optional[str]
+    """Custom AWS endpoint"""
+
+    scale_on_delayed: bool
+    """Scale on delayed messages"""
+
+    scale_on_flight: bool
+    """Scale on in-flight messages"""
+
+
+class ContainerScaleTriggers(TypedDict, total=False):
+    cpu: Optional[ContainerScaleTriggersCPU]
+    """CPU trigger configuration"""
+
+    gpu_memory: Optional[ContainerScaleTriggersGPUMemory]
+    """GPU memory trigger configuration.
+
+    Calculated by DCGM_FI_DEV_MEM_COPY_UTIL metric
+    """
+
+    gpu_utilization: Optional[ContainerScaleTriggersGPUUtilization]
+    """GPU utilization trigger configuration.
+
+    Calculated by DCGM_FI_DEV_GPU_UTIL metric
+    """
+
+    http: Optional[ContainerScaleTriggersHTTP]
+    """HTTP trigger configuration"""
+
+    memory: Optional[ContainerScaleTriggersMemory]
+    """Memory trigger configuration"""
+
+    sqs: Optional[ContainerScaleTriggersSqs]
+    """SQS trigger configuration"""
+
+
+class ContainerScale(TypedDict, total=False):
+    max: Required[int]
+    """Maximum scale for the container"""
+
+    min: Required[int]
+    """Minimum scale for the container"""
+
+    cooldown_period: int
+    """Cooldown period between scaling actions in seconds"""
+
+    polling_interval: int
+    """Polling interval for scaling triggers in seconds"""
+
+    triggers: ContainerScaleTriggers
+    """Triggers for scaling actions"""
+
+
+class Container(TypedDict, total=False):
+    region_id: Required[Optional[int]]
+    """Region id for the container"""
+
+    scale: Required[Optional[ContainerScale]]
+    """Scale for the container"""
+
+
+class Logging(TypedDict, total=False):
+    destination_region_id: Optional[int]
+    """ID of the region in which the logs will be stored"""
+
+    enabled: bool
+    """Enable or disable log streaming"""
+
+    retention_policy: Optional[LaasIndexRetentionPolicyParam]
+    """Logs retention policy"""
+
+    topic_name: Optional[str]
+    """The topic name to stream logs to"""
+
+
+class Probes(TypedDict, total=False):
+    liveness_probe: Optional[ContainerProbeConfigCreateParam]
+    """Liveness probe configuration"""
+
+    readiness_probe: Optional[ContainerProbeConfigCreateParam]
+    """Readiness probe configuration"""
+
+    startup_probe: Optional[ContainerProbeConfigCreateParam]
+    """Startup probe configuration"""

gcore/types/cloud/inference/deployments/__init__.py

@@ -0,0 +1,5 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .log_list_params import LogListParams as LogListParams

gcore/types/cloud/inference/deployments/log_list_params.py

@@ -0,0 +1,28 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["LogListParams"]
+
+
+class LogListParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    limit: int
+    """Optional. Limit the number of returned items"""
+
+    offset: int
+    """Optional.
+
+    Offset value is used to exclude the first set of records from the result
+    """
+
+    order_by: Literal["time.asc", "time.desc"]
+    """Order by field"""
+
+    region_id: Optional[int]
+    """Region ID"""

gcore/types/cloud/inference/flavor_list_params.py

@@ -0,0 +1,18 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import TypedDict
+
+__all__ = ["FlavorListParams"]
+
+
+class FlavorListParams(TypedDict, total=False):
+    limit: int
+    """Optional. Limit the number of returned items"""
+
+    offset: int
+    """Optional.
+
+    Offset value is used to exclude the first set of records from the result
+    """

gcore/types/cloud/inference/inference.py

@@ -0,0 +1,95 @@
+# 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 .container import Container
+from ...._models import BaseModel
+from ..inference_probes import InferenceProbes
+from ..ingress_opts_out import IngressOptsOut
+
+__all__ = ["Inference"]
+
+
+class Inference(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[IngressOptsOut] = 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."""
+
+    probes: Optional[InferenceProbes] = 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"]
+    """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.
+    - `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.
+    """

gcore/types/cloud/inference/inference_apikey_secret.py

@@ -0,0 +1,15 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal
+
+from ...._models import BaseModel
+
+__all__ = ["InferenceApikeySecret"]
+
+
+class InferenceApikeySecret(BaseModel):
+    secret: str
+    """API key secret"""
+
+    status: Literal["PENDING", "READY"]
+    """API key status"""

gcore/types/cloud/inference/inference_flavor.py

@@ -0,0 +1,34 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from ...._models import BaseModel
+
+__all__ = ["InferenceFlavor"]
+
+
+class InferenceFlavor(BaseModel):
+    cpu: float
+    """Inference flavor cpu count."""
+
+    description: str
+    """Inference flavor description."""
+
+    gpu: int
+    """Inference flavor gpu count."""
+
+    gpu_compute_capability: str
+    """Inference flavor gpu compute capability."""
+
+    gpu_memory: float
+    """Inference flavor gpu memory in Gi."""
+
+    gpu_model: str
+    """Inference flavor gpu model."""
+
+    is_gpu_shared: bool
+    """Inference flavor is gpu shared."""
+
+    memory: float
+    """Inference flavor memory in Gi."""
+
+    name: str
+    """Inference flavor name."""

gcore/types/cloud/inference/inference_log.py

@@ -0,0 +1,21 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from datetime import datetime
+
+from ...._models import BaseModel
+
+__all__ = ["InferenceLog"]
+
+
+class InferenceLog(BaseModel):
+    message: str
+    """Log message."""
+
+    pod: str
+    """Pod name."""
+
+    region_id: int
+    """Region ID where the container is deployed."""
+
+    time: datetime
+    """Log message timestamp in ISO 8601 format."""