gcore 0.1.0__py3-none-any.whl

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."""

gcore/types/cloud/inference/inference_registry_credential.py

@@ -0,0 +1,19 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from ...._models import BaseModel
+
+__all__ = ["InferenceRegistryCredential"]
+
+
+class InferenceRegistryCredential(BaseModel):
+    name: str
+    """Registry credential name."""
+
+    project_id: int
+    """Project ID to which the inference registry credentials belongs."""
+
+    registry_url: str
+    """Registry URL."""
+
+    username: str
+    """Registry username."""

gcore/types/cloud/inference/inference_registry_credential_full.py

@@ -0,0 +1,22 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from ...._models import BaseModel
+
+__all__ = ["InferenceRegistryCredentialFull"]
+
+
+class InferenceRegistryCredentialFull(BaseModel):
+    name: str
+    """Registry credential name."""
+
+    password: str
+    """Registry password."""
+
+    project_id: int
+    """Project ID to which the inference registry credentials belongs."""
+
+    registry_url: str
+    """Registry URL."""
+
+    username: str
+    """Registry username."""

gcore/types/cloud/inference/inference_secret.py

@@ -0,0 +1,17 @@
+# 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"]
+
+
+class InferenceSecret(BaseModel):
+    data: AwsIamData
+    """Secret data."""
+
+    name: str
+    """Secret name."""
+
+    type: str
+    """Secret type."""

gcore/types/cloud/inference/mlcatalog_model_card.py

@@ -0,0 +1,65 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from pydantic import Field as FieldInfo
+
+from ...._models import BaseModel
+
+__all__ = ["MlcatalogModelCard"]
+
+
+class MlcatalogModelCard(BaseModel):
+    id: str
+    """Model ID."""
+
+    category: Optional[str] = None
+    """Category of the model."""
+
+    default_flavor_name: Optional[str] = None
+    """Default flavor for the model."""
+
+    description: str
+    """Description of the model."""
+
+    developer: Optional[str] = None
+    """Developer of the model."""
+
+    documentation_page: Optional[str] = None
+    """Path to the documentation page."""
+
+    eula_url: Optional[str] = None
+    """URL to the EULA text."""
+
+    example_curl_request: Optional[str] = None
+    """Example curl request to the model."""
+
+    has_eula: bool
+    """Whether the model has an EULA."""
+
+    image_registry_id: Optional[str] = None
+    """Image registry of the model."""
+
+    image_url: str
+    """Image URL of the model."""
+
+    inference_backend: Optional[str] = None
+    """Describing underlying inference engine."""
+
+    inference_frontend: Optional[str] = None
+    """Describing model frontend type."""
+
+    api_model_id: Optional[str] = FieldInfo(alias="model_id", default=None)
+    """Model name to perform inference call."""
+
+    name: str
+    """Name of the model."""
+
+    openai_compatibility: Optional[str] = None
+    """OpenAI compatibility level."""
+
+    port: int
+    """Port on which the model runs."""
+
+    version: Optional[str] = None
+    """Version of the model."""

gcore/types/cloud/inference/mlcatalog_order_by_choices.py

@@ -0,0 +1,7 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["MlcatalogOrderByChoices"]
+
+MlcatalogOrderByChoices: TypeAlias = Literal["name.asc", "name.desc"]

gcore/types/cloud/inference/model_list_params.py

@@ -0,0 +1,23 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import TypedDict
+
+from .mlcatalog_order_by_choices import MlcatalogOrderByChoices
+
+__all__ = ["ModelListParams"]
+
+
+class ModelListParams(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
+    """
+
+    order_by: MlcatalogOrderByChoices
+    """Order instances by transmitted fields and directions"""

gcore/types/cloud/inference/registry_credential_create_params.py

@@ -0,0 +1,24 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Required, TypedDict
+
+__all__ = ["RegistryCredentialCreateParams"]
+
+
+class RegistryCredentialCreateParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    name: Required[str]
+    """Registry credential name."""
+
+    password: Required[str]
+    """Registry password."""
+
+    registry_url: Required[str]
+    """Registry URL."""
+
+    username: Required[str]
+    """Registry username."""

gcore/types/cloud/inference/registry_credential_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__ = ["RegistryCredentialListParams"]
+
+
+class RegistryCredentialListParams(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/registry_credential_replace_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 Required, TypedDict
+
+__all__ = ["RegistryCredentialReplaceParams"]
+
+
+class RegistryCredentialReplaceParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    password: Required[str]
+    """Registry password."""
+
+    registry_url: Required[str]
+    """Registry URL."""
+
+    username: Required[str]
+    """Registry username."""

gcore/types/cloud/inference/secret_create_params.py

@@ -0,0 +1,23 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Required, TypedDict
+
+from ..aws_iam_data_param import AwsIamDataParam
+
+__all__ = ["SecretCreateParams"]
+
+
+class SecretCreateParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    data: Required[AwsIamDataParam]
+    """Secret data."""
+
+    name: Required[str]
+    """Secret name."""
+
+    type: Required[str]
+    """Secret type. Currently only `aws-iam` is supported."""

gcore/types/cloud/inference/secret_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__ = ["SecretListParams"]
+
+
+class SecretListParams(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/secret_replace_params.py

@@ -0,0 +1,20 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Required, TypedDict
+
+from ..aws_iam_data_param import AwsIamDataParam
+
+__all__ = ["SecretReplaceParams"]
+
+
+class SecretReplaceParams(TypedDict, total=False):
+    project_id: int
+    """Project ID"""
+
+    data: Required[AwsIamDataParam]
+    """Secret data."""
+
+    type: Required[str]
+    """Secret type."""

gcore/types/cloud/inference_probes.py

@@ -0,0 +1,19 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from ..._models import BaseModel
+from .container_probe_config import ContainerProbeConfig
+
+__all__ = ["InferenceProbes"]
+
+
+class InferenceProbes(BaseModel):
+    liveness_probe: Optional[ContainerProbeConfig] = None
+    """Liveness probe configuration"""
+
+    readiness_probe: Optional[ContainerProbeConfig] = None
+    """Readiness probe configuration"""
+
+    startup_probe: Optional[ContainerProbeConfig] = None
+    """Startup probe configuration"""

gcore/types/cloud/ingress_opts_out.py

@@ -0,0 +1,16 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from ..._models import BaseModel
+
+__all__ = ["IngressOptsOut"]
+
+
+class IngressOptsOut(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.
+    """

gcore/types/cloud/ingress_opts_param.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__ = ["IngressOptsParam"]
+
+
+class IngressOptsParam(TypedDict, total=False):
+    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.
+    """