scale-gp-beta 0.1.0a2__py3-none-any.whl

scale_gp/types/file_list.py

@@ -0,0 +1,27 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .file import File
+from .._models import BaseModel
+
+__all__ = ["FileList"]
+
+
+class FileList(BaseModel):
+    has_more: bool
+    """Whether there are more items left to be fetched."""
+
+    items: List[File]
+
+    total: int
+    """The total of items that match the query.
+
+    This is greater than or equal to the number of items returned.
+    """
+
+    limit: Optional[int] = None
+    """The maximum number of items to return."""
+
+    object: Optional[Literal["list"]] = None

scale_gp/types/file_list_params.py

@@ -0,0 +1,16 @@
+# 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 TypedDict
+
+__all__ = ["FileListParams"]
+
+
+class FileListParams(TypedDict, total=False):
+    ending_before: Optional[str]
+
+    limit: int
+
+    starting_after: Optional[str]

scale_gp/types/file_update_params.py

@@ -0,0 +1,12 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import TypedDict
+
+__all__ = ["FileUpdateParams"]
+
+
+class FileUpdateParams(TypedDict, total=False):
+    tags: Dict[str, object]

scale_gp/types/files/__init__.py

@@ -0,0 +1,3 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations

scale_gp/types/inference_create_params.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Required, TypedDict
+
+__all__ = ["InferenceCreateParams", "InferenceConfiguration"]
+
+
+class InferenceCreateParams(TypedDict, total=False):
+    model: Required[str]
+    """model specified as `vendor/name` (ex. openai/gpt-5)"""
+
+    args: Dict[str, object]
+    """Arguments passed into model"""
+
+    inference_configuration: InferenceConfiguration
+    """Vendor specific configuration"""
+
+
+class InferenceConfiguration(TypedDict, total=False):
+    num_retries: int
+
+    timeout_seconds: int

scale_gp/types/inference_create_response.py

@@ -0,0 +1,11 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union
+from typing_extensions import TypeAlias
+
+from .inference_response import InferenceResponse
+from .inference_response_chunk import InferenceResponseChunk
+
+__all__ = ["InferenceCreateResponse"]
+
+InferenceCreateResponse: TypeAlias = Union[InferenceResponse, InferenceResponseChunk]

scale_gp/types/inference_model.py

@@ -0,0 +1,167 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import TYPE_CHECKING, Dict, List, Union, Optional
+from datetime import datetime
+from typing_extensions import Literal, TypeAlias
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = [
+    "InferenceModel",
+    "VendorConfiguration",
+    "VendorConfigurationLaunchVendorConfiguration",
+    "VendorConfigurationLaunchVendorConfigurationModelImage",
+    "VendorConfigurationLaunchVendorConfigurationModelInfra",
+    "VendorConfigurationLlmEngineVendorConfiguration",
+]
+
+
+class VendorConfigurationLaunchVendorConfigurationModelImage(BaseModel):
+    command: List[str]
+
+    registry: str
+
+    repository: str
+
+    tag: str
+
+    env_vars: Optional[Dict[str, object]] = None
+
+    healthcheck_route: Optional[str] = None
+
+    predict_route: Optional[str] = None
+
+    readiness_delay: Optional[int] = None
+
+    request_schema: Optional[Dict[str, object]] = None
+
+    response_schema: Optional[Dict[str, object]] = None
+
+    streaming_command: Optional[List[str]] = None
+
+    streaming_predict_route: Optional[str] = None
+
+
+class VendorConfigurationLaunchVendorConfigurationModelInfra(BaseModel):
+    cpus: Union[str, int, None] = None
+
+    endpoint_type: Optional[Literal["async", "sync", "streaming"]] = None
+
+    gpu_type: Optional[
+        Literal[
+            "nvidia-tesla-t4",
+            "nvidia-ampere-a10",
+            "nvidia-ampere-a100",
+            "nvidia-ampere-a100e",
+            "nvidia-hopper-h100",
+            "nvidia-hopper-h100-1g20gb",
+            "nvidia-hopper-h100-3g40gb",
+        ]
+    ] = None
+
+    gpus: Optional[int] = None
+
+    high_priority: Optional[bool] = None
+
+    labels: Optional[Dict[str, str]] = None
+
+    max_workers: Optional[int] = None
+
+    memory: Optional[str] = None
+
+    min_workers: Optional[int] = None
+
+    per_worker: Optional[int] = None
+
+    public_inference: Optional[bool] = None
+
+    storage: Optional[str] = None
+
+
+class VendorConfigurationLaunchVendorConfiguration(BaseModel):
+    api_model_image: VendorConfigurationLaunchVendorConfigurationModelImage = FieldInfo(alias="model_image")
+
+    api_model_infra: VendorConfigurationLaunchVendorConfigurationModelInfra = FieldInfo(alias="model_infra")
+
+
+class VendorConfigurationLlmEngineVendorConfiguration(BaseModel):
+    model: str
+
+    checkpoint_path: Optional[str] = None
+
+    cpus: Optional[int] = None
+
+    default_callback_url: Optional[str] = None
+
+    endpoint_type: Optional[str] = None
+
+    gpu_type: Optional[str] = None
+
+    gpus: Optional[int] = None
+
+    high_priority: Optional[bool] = None
+
+    inference_framework: Optional[str] = None
+
+    inference_framework_image_tag: Optional[str] = None
+
+    labels: Optional[Dict[str, str]] = None
+
+    max_workers: Optional[int] = None
+
+    memory: Optional[str] = None
+
+    min_workers: Optional[int] = None
+
+    nodes_per_worker: Optional[int] = None
+
+    num_shards: Optional[int] = None
+
+    per_worker: Optional[int] = None
+
+    post_inference_hooks: Optional[List[str]] = None
+
+    public_inference: Optional[bool] = None
+
+    quantize: Optional[str] = None
+
+    source: Optional[str] = None
+
+    storage: Optional[str] = None
+
+    if TYPE_CHECKING:
+        # Stub to indicate that arbitrary properties are accepted.
+        # To access properties that are not valid identifiers you can use `getattr`, e.g.
+        # `getattr(obj, '$type')`
+        def __getattr__(self, attr: str) -> object: ...
+
+
+VendorConfiguration: TypeAlias = Union[
+    VendorConfigurationLaunchVendorConfiguration, VendorConfigurationLlmEngineVendorConfiguration
+]
+
+
+class InferenceModel(BaseModel):
+    id: str
+
+    created_at: datetime
+
+    created_by_user_id: str
+
+    api_model_type: Literal["generic", "completion", "chat_completion"] = FieldInfo(alias="model_type")
+
+    api_model_vendor: Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"] = (
+        FieldInfo(alias="model_vendor")
+    )
+
+    name: str
+
+    status: Literal["failed", "ready", "deploying"]
+
+    vendor_configuration: VendorConfiguration
+
+    api_model_metadata: Optional[Dict[str, object]] = FieldInfo(alias="model_metadata", default=None)
+
+    object: Optional[Literal["model"]] = None

scale_gp/types/inference_model_list.py

@@ -0,0 +1,27 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+from .inference_model import InferenceModel
+
+__all__ = ["InferenceModelList"]
+
+
+class InferenceModelList(BaseModel):
+    has_more: bool
+    """Whether there are more items left to be fetched."""
+
+    items: List[InferenceModel]
+
+    total: int
+    """The total of items that match the query.
+
+    This is greater than or equal to the number of items returned.
+    """
+
+    limit: Optional[int] = None
+    """The maximum number of items to return."""
+
+    object: Optional[Literal["list"]] = None

scale_gp/types/inference_response.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["InferenceResponse"]
+
+
+class InferenceResponse(BaseModel):
+    response: object
+
+    object: Optional[Literal["generic_inference"]] = None

scale_gp/types/inference_response_chunk.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["InferenceResponseChunk"]
+
+
+class InferenceResponseChunk(BaseModel):
+    response: object
+
+    object: Optional[Literal["generic_inference.chunk"]] = None

scale_gp/types/model_create_params.py

@@ -0,0 +1,165 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union
+from typing_extensions import Literal, Required, TypeAlias, TypedDict
+
+__all__ = [
+    "ModelCreateParams",
+    "LaunchModelCreateRequest",
+    "LaunchModelCreateRequestVendorConfiguration",
+    "LaunchModelCreateRequestVendorConfigurationModelImage",
+    "LaunchModelCreateRequestVendorConfigurationModelInfra",
+    "LlmEngineModelCreateRequest",
+    "LlmEngineModelCreateRequestVendorConfiguration",
+]
+
+
+class LaunchModelCreateRequest(TypedDict, total=False):
+    name: Required[str]
+    """Unique name to reference your model"""
+
+    vendor_configuration: Required[LaunchModelCreateRequestVendorConfiguration]
+
+    model_metadata: Dict[str, object]
+
+    model_type: Literal["generic"]
+
+    model_vendor: Literal["launch"]
+
+    on_conflict: Literal["error", "update"]
+
+
+class LaunchModelCreateRequestVendorConfigurationModelImage(TypedDict, total=False):
+    command: Required[List[str]]
+
+    registry: Required[str]
+
+    repository: Required[str]
+
+    tag: Required[str]
+
+    env_vars: Dict[str, object]
+
+    healthcheck_route: str
+
+    predict_route: str
+
+    readiness_delay: int
+
+    request_schema: Dict[str, object]
+
+    response_schema: Dict[str, object]
+
+    streaming_command: List[str]
+
+    streaming_predict_route: str
+
+
+class LaunchModelCreateRequestVendorConfigurationModelInfra(TypedDict, total=False):
+    cpus: Union[str, int]
+
+    endpoint_type: Literal["async", "sync", "streaming"]
+
+    gpu_type: Literal[
+        "nvidia-tesla-t4",
+        "nvidia-ampere-a10",
+        "nvidia-ampere-a100",
+        "nvidia-ampere-a100e",
+        "nvidia-hopper-h100",
+        "nvidia-hopper-h100-1g20gb",
+        "nvidia-hopper-h100-3g40gb",
+    ]
+
+    gpus: int
+
+    high_priority: bool
+
+    labels: Dict[str, str]
+
+    max_workers: int
+
+    memory: str
+
+    min_workers: int
+
+    per_worker: int
+
+    public_inference: bool
+
+    storage: str
+
+
+class LaunchModelCreateRequestVendorConfiguration(TypedDict, total=False):
+    model_image: Required[LaunchModelCreateRequestVendorConfigurationModelImage]
+
+    model_infra: Required[LaunchModelCreateRequestVendorConfigurationModelInfra]
+
+
+class LlmEngineModelCreateRequest(TypedDict, total=False):
+    name: Required[str]
+    """Unique name to reference your model"""
+
+    vendor_configuration: Required[LlmEngineModelCreateRequestVendorConfiguration]
+
+    model_metadata: Dict[str, object]
+
+    model_type: Literal["chat_completion"]
+
+    model_vendor: Literal["llmengine"]
+
+    on_conflict: Literal["error", "update"]
+
+
+class LlmEngineModelCreateRequestVendorConfigurationTyped(TypedDict, total=False):
+    model: Required[str]
+
+    checkpoint_path: str
+
+    cpus: int
+
+    default_callback_url: str
+
+    endpoint_type: str
+
+    gpu_type: str
+
+    gpus: int
+
+    high_priority: bool
+
+    inference_framework: str
+
+    inference_framework_image_tag: str
+
+    labels: Dict[str, str]
+
+    max_workers: int
+
+    memory: str
+
+    min_workers: int
+
+    nodes_per_worker: int
+
+    num_shards: int
+
+    per_worker: int
+
+    post_inference_hooks: List[str]
+
+    public_inference: bool
+
+    quantize: str
+
+    source: str
+
+    storage: str
+
+
+LlmEngineModelCreateRequestVendorConfiguration: TypeAlias = Union[
+    LlmEngineModelCreateRequestVendorConfigurationTyped, Dict[str, object]
+]
+
+ModelCreateParams: TypeAlias = Union[LaunchModelCreateRequest, LlmEngineModelCreateRequest]

scale_gp/types/model_delete_response.py

@@ -0,0 +1,16 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["ModelDeleteResponse"]
+
+
+class ModelDeleteResponse(BaseModel):
+    id: str
+
+    deleted: bool
+
+    object: Optional[Literal["model"]] = None

scale_gp/types/model_list_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 import Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["ModelListParams"]
+
+
+class ModelListParams(TypedDict, total=False):
+    ending_before: Optional[str]
+
+    limit: int
+
+    model_vendor: Optional[Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"]]
+
+    name: Optional[str]
+
+    starting_after: Optional[str]

scale_gp/types/model_update_params.py

@@ -0,0 +1,161 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union
+from typing_extensions import Literal, Required, TypeAlias, TypedDict
+
+__all__ = [
+    "ModelUpdateParams",
+    "DefaultModelPatchRequest",
+    "ModelConfigurationPatchRequest",
+    "ModelConfigurationPatchRequestVendorConfiguration",
+    "ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfiguration",
+    "ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelImage",
+    "ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelInfra",
+    "ModelConfigurationPatchRequestVendorConfigurationPartialLlmEngineVendorConfiguration",
+    "SwapNamesModelPatchRequest",
+]
+
+
+class DefaultModelPatchRequest(TypedDict, total=False):
+    model_metadata: Dict[str, object]
+
+
+class ModelConfigurationPatchRequest(TypedDict, total=False):
+    vendor_configuration: Required[ModelConfigurationPatchRequestVendorConfiguration]
+
+    model_metadata: Dict[str, object]
+
+
+class ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelImage(
+    TypedDict, total=False
+):
+    command: List[str]
+
+    env_vars: Dict[str, object]
+
+    healthcheck_route: str
+
+    predict_route: str
+
+    readiness_delay: int
+
+    registry: str
+
+    repository: str
+
+    request_schema: Dict[str, object]
+
+    response_schema: Dict[str, object]
+
+    streaming_command: List[str]
+
+    streaming_predict_route: str
+
+    tag: str
+
+
+class ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelInfra(
+    TypedDict, total=False
+):
+    cpus: Union[str, int]
+
+    endpoint_type: Literal["async", "sync", "streaming"]
+
+    gpu_type: Literal[
+        "nvidia-tesla-t4",
+        "nvidia-ampere-a10",
+        "nvidia-ampere-a100",
+        "nvidia-ampere-a100e",
+        "nvidia-hopper-h100",
+        "nvidia-hopper-h100-1g20gb",
+        "nvidia-hopper-h100-3g40gb",
+    ]
+
+    gpus: int
+
+    high_priority: bool
+
+    labels: Dict[str, str]
+
+    max_workers: int
+
+    memory: str
+
+    min_workers: int
+
+    per_worker: int
+
+    public_inference: bool
+
+    storage: str
+
+
+class ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfiguration(TypedDict, total=False):
+    model_image: ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelImage
+
+    model_infra: ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfigurationModelInfra
+
+
+class ModelConfigurationPatchRequestVendorConfigurationPartialLlmEngineVendorConfiguration(TypedDict, total=False):
+    checkpoint_path: str
+
+    cpus: int
+
+    default_callback_url: str
+
+    endpoint_type: str
+
+    gpu_type: str
+
+    gpus: int
+
+    high_priority: bool
+
+    inference_framework: str
+
+    inference_framework_image_tag: str
+
+    labels: Dict[str, str]
+
+    max_workers: int
+
+    memory: str
+
+    min_workers: int
+
+    model: str
+
+    nodes_per_worker: int
+
+    num_shards: int
+
+    per_worker: int
+
+    post_inference_hooks: List[str]
+
+    public_inference: bool
+
+    quantize: str
+
+    source: str
+
+    storage: str
+
+
+ModelConfigurationPatchRequestVendorConfiguration: TypeAlias = Union[
+    ModelConfigurationPatchRequestVendorConfigurationPartialLaunchVendorConfiguration,
+    ModelConfigurationPatchRequestVendorConfigurationPartialLlmEngineVendorConfiguration,
+]
+
+
+class SwapNamesModelPatchRequest(TypedDict, total=False):
+    name: Required[str]
+
+    on_conflict: Literal["error", "swap"]
+
+
+ModelUpdateParams: TypeAlias = Union[
+    DefaultModelPatchRequest, ModelConfigurationPatchRequest, SwapNamesModelPatchRequest
+]