gmicloud 0.1.1__tar.gz → 0.1.2__tar.gz

{gmicloud-0.1.1 → gmicloud-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gmicloud
-Version: 0.1.1
+Version: 0.1.2
 Summary: GMI Cloud Python SDK
 Author-email: GMI <gmi@gmitec.net>
 License: MIT
@@ -76,10 +76,10 @@ client = Client()
 
 # Schedule and start a task from an artifact template
 task = client.create_task_from_artifact_template(
-    "llama31_8b_template_001",
+    "qwen_2.5_14b_instruct_template_001",
     TaskScheduling(
         scheduling_oneoff=OneOffScheduling(
-            trigger_timestamp=int(datetime.now().timestamp()) + 60,  # Delay by 1 min
+            trigger_timestamp=int(datetime.now().timestamp()) + 10,  # Delay by 10 seconds
             min_replicas=1,
             max_replicas=10,
         )
@@ -104,7 +104,7 @@ def create_artifact_from_template(client):
     # List all available templates
     templates = artifact_manager.get_artifact_templates()
     for template in templates:
-        if template.artifact_name == "Llama3.1 8B":
+        if template.artifact_template_id == "qwen_2.5_14b_instruct_template_001":
             return artifact_manager.create_artifact_from_template(
                 artifact_template_id=template.artifact_template_id
             )
@@ -132,19 +132,19 @@ def create_task_and_start(client, artifact_id):
     task = task_manager.create_task(Task(
         config=TaskConfig(
             ray_task_config=RayTaskConfig(
-                ray_version="latest-py311-gpu",
+                ray_version="2.40.0-py310-gpu",
                 file_path="serve",
                 artifact_id=artifact_id,
                 deployment_name="app",
                 replica_resource=ReplicaResource(
-                    cpu=24,
-                    ram_gb=128,
-                    gpu=2,
+                    cpu=10,
+                    ram_gb=100,
+                    gpu=1,
                 ),
             ),
             task_scheduling=TaskScheduling(
                 scheduling_oneoff=OneOffScheduling(
-                    trigger_timestamp=int(datetime.now().timestamp()) + 60,
+                    trigger_timestamp=int(datetime.now().timestamp()) + 10,
                     min_replicas=1,
                     max_replicas=10,
                 )
@@ -158,7 +158,7 @@ def create_task_and_start(client, artifact_id):
 
 ### (c) Query the Model Endpoint
 
-Once the task is ready, use the endpoint for inference:
+Once the task is running, use the endpoint for inference:
 
 ```python
 from examples.completion import call_chat_completion
@@ -198,8 +198,8 @@ password: Optional[str] = ""
 ## Notes & Troubleshooting
 
 Ensure Credentials are Correct: Double-check your environment variables or parameters passed into the Client object.
-Artifact Status: It may take a few minutes for an artifact or task to transition to the "ready" state.
-Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "ready".
+Artifact Status: It may take a few minutes for an artifact or task to transition to the "running" state.
+Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "running".
 Default OpenAI Key: By default, the OpenAI API base URL is derived from the endpoint provided by GMI.
 
 ## Contributing

{gmicloud-0.1.1 → gmicloud-0.1.2}/README.md

@@ -64,10 +64,10 @@ client = Client()
 
 # Schedule and start a task from an artifact template
 task = client.create_task_from_artifact_template(
-    "llama31_8b_template_001",
+    "qwen_2.5_14b_instruct_template_001",
     TaskScheduling(
         scheduling_oneoff=OneOffScheduling(
-            trigger_timestamp=int(datetime.now().timestamp()) + 60,  # Delay by 1 min
+            trigger_timestamp=int(datetime.now().timestamp()) + 10,  # Delay by 10 seconds
             min_replicas=1,
             max_replicas=10,
         )
@@ -92,7 +92,7 @@ def create_artifact_from_template(client):
     # List all available templates
     templates = artifact_manager.get_artifact_templates()
     for template in templates:
-        if template.artifact_name == "Llama3.1 8B":
+        if template.artifact_template_id == "qwen_2.5_14b_instruct_template_001":
             return artifact_manager.create_artifact_from_template(
                 artifact_template_id=template.artifact_template_id
             )
@@ -120,19 +120,19 @@ def create_task_and_start(client, artifact_id):
     task = task_manager.create_task(Task(
         config=TaskConfig(
             ray_task_config=RayTaskConfig(
-                ray_version="latest-py311-gpu",
+                ray_version="2.40.0-py310-gpu",
                 file_path="serve",
                 artifact_id=artifact_id,
                 deployment_name="app",
                 replica_resource=ReplicaResource(
-                    cpu=24,
-                    ram_gb=128,
-                    gpu=2,
+                    cpu=10,
+                    ram_gb=100,
+                    gpu=1,
                 ),
             ),
             task_scheduling=TaskScheduling(
                 scheduling_oneoff=OneOffScheduling(
-                    trigger_timestamp=int(datetime.now().timestamp()) + 60,
+                    trigger_timestamp=int(datetime.now().timestamp()) + 10,
                     min_replicas=1,
                     max_replicas=10,
                 )
@@ -146,7 +146,7 @@ def create_task_and_start(client, artifact_id):
 
 ### (c) Query the Model Endpoint
 
-Once the task is ready, use the endpoint for inference:
+Once the task is running, use the endpoint for inference:
 
 ```python
 from examples.completion import call_chat_completion
@@ -186,8 +186,8 @@ password: Optional[str] = ""
 ## Notes & Troubleshooting
 
 Ensure Credentials are Correct: Double-check your environment variables or parameters passed into the Client object.
-Artifact Status: It may take a few minutes for an artifact or task to transition to the "ready" state.
-Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "ready".
+Artifact Status: It may take a few minutes for an artifact or task to transition to the "running" state.
+Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "running".
 Default OpenAI Key: By default, the OpenAI API base URL is derived from the endpoint provided by GMI.
 
 ## Contributing

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud/__init__.py

@@ -5,7 +5,7 @@ from ._internal._models import (
     Task,
     TaskOwner,
     TaskConfig,
-    TaskInfo,
+    EndpointInfo,
     RayTaskConfig,
     TaskScheduling,
     ReplicaResource,
@@ -13,7 +13,6 @@ from ._internal._models import (
     DailyScheduling,
     DailyTrigger,
     ArtifactTemplate,
-    CreateArtifactFromTemplateResponse
 )
 from ._internal._enums import (
     BuildStatus,
@@ -29,7 +28,7 @@ __all__ = [
     "Task",
     "TaskOwner",
     "TaskConfig",
-    "TaskInfo",
+    "EndpointInfo",
     "RayTaskConfig",
     "TaskScheduling",
     "ReplicaResource",
@@ -39,5 +38,4 @@ __all__ = [
     "ArtifactTemplate",
     "BuildStatus",
     "TaskEndpointStatus",
-    "CreateArtifactFromTemplateResponse"
 ]

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud/_internal/_client/_http_client.py

@@ -60,7 +60,6 @@ class HTTPClient:
                 else:
                     error_message = response.json().get('message', 'Unknown error')
                 raise APIError(f"HTTP Request failed: {error_message}")
-
             # Raise for HTTP errors
             response.raise_for_status()
 

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud/_internal/_enums.py

@@ -14,6 +14,7 @@ class BuildStatus(str, Enum):
 
 
 class TaskEndpointStatus(str, Enum):
+    UNKNOWN = ""
     PENDING = "pending"
     DEPLOYING = "deploying"
     SCALING = "scaling"
@@ -21,3 +22,4 @@ class TaskEndpointStatus(str, Enum):
     ARCHIVED = "archived"
     READY = "ready"
     UNREADY = "unready"
+    NEW = "new"

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud/_internal/_models.py

@@ -216,7 +216,7 @@ class RayTaskConfig(BaseModel):
     file_path: Optional[str] = ""  # Path to the task file in storage.
     deployment_name: Optional[str] = ""  # Name of the deployment.
     replica_resource: Optional[ReplicaResource] = None  # Resources allocated for task replicas.
-    volume_mounts: Optional[VolumeMount] = None  # Configuration for mounted volumes.
+    volume_mounts: Optional[List[VolumeMount]] = None  # Configuration for mounted volumes.
 
 
 class OneOffScheduling(BaseModel):
@@ -265,12 +265,12 @@ class TaskConfig(BaseModel):
     last_update_timestamp: Optional[int] = 0  # Timestamp when the task was last updated.
 
 
-class TaskInfo(BaseModel):
+class EndpointInfo(BaseModel):
     """
-    Additional information about a task.
+    Additional information about the task endpoint.
     """
     endpoint_status: Optional[TaskEndpointStatus] = None  # Current status of the task (e.g., running, stopped).
-    endpoint: Optional[str] = ""  # API endpoint exposed by the task, if applicable.
+    endpoint_url: Optional[str] = ""  # URL for accessing the task endpoint.
 
 
 class UserPreference(BaseModel):
@@ -288,7 +288,8 @@ class Task(BaseModel):
     task_id: Optional[str] = None  # Unique identifier for the task.
     owner: Optional[TaskOwner] = None  # Ownership information of the task.
     config: Optional[TaskConfig] = None  # Configuration data for the task.
-    info: Optional[TaskInfo] = None  # Additional information about the task.
+    endpoint_info: Optional[EndpointInfo] = None  # Additional information about the task endpoint.
+    cluster_endpoints: Optional[List[EndpointInfo]] = None  # Endpoints for the task cluster.
     task_status: Optional[str] = ""  # Status of the task.
     readiness_status: Optional[str] = ""  # Readiness status of the task.
     user_preference: Optional[UserPreference] = None  # User preference for the task.

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud/client.py

@@ -7,7 +7,7 @@ from ._internal._client._iam_client import IAMClient
 from ._internal._manager._artifact_manager import ArtifactManager
 from ._internal._manager._task_manager import TaskManager
 from ._internal._enums import BuildStatus
-from ._internal._models import Task, TaskConfig, RayTaskConfig, TaskScheduling, OneOffScheduling, ReplicaResource
+from ._internal._models import Task, TaskConfig, RayTaskConfig, TaskScheduling, ReplicaResource
 
 
 class Client:

{gmicloud-0.1.1 → gmicloud-0.1.2}/gmicloud.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: gmicloud
-Version: 0.1.1
+Version: 0.1.2
 Summary: GMI Cloud Python SDK
 Author-email: GMI <gmi@gmitec.net>
 License: MIT
@@ -76,10 +76,10 @@ client = Client()
 
 # Schedule and start a task from an artifact template
 task = client.create_task_from_artifact_template(
-    "llama31_8b_template_001",
+    "qwen_2.5_14b_instruct_template_001",
     TaskScheduling(
         scheduling_oneoff=OneOffScheduling(
-            trigger_timestamp=int(datetime.now().timestamp()) + 60,  # Delay by 1 min
+            trigger_timestamp=int(datetime.now().timestamp()) + 10,  # Delay by 10 seconds
             min_replicas=1,
             max_replicas=10,
         )
@@ -104,7 +104,7 @@ def create_artifact_from_template(client):
     # List all available templates
     templates = artifact_manager.get_artifact_templates()
     for template in templates:
-        if template.artifact_name == "Llama3.1 8B":
+        if template.artifact_template_id == "qwen_2.5_14b_instruct_template_001":
             return artifact_manager.create_artifact_from_template(
                 artifact_template_id=template.artifact_template_id
             )
@@ -132,19 +132,19 @@ def create_task_and_start(client, artifact_id):
     task = task_manager.create_task(Task(
         config=TaskConfig(
             ray_task_config=RayTaskConfig(
-                ray_version="latest-py311-gpu",
+                ray_version="2.40.0-py310-gpu",
                 file_path="serve",
                 artifact_id=artifact_id,
                 deployment_name="app",
                 replica_resource=ReplicaResource(
-                    cpu=24,
-                    ram_gb=128,
-                    gpu=2,
+                    cpu=10,
+                    ram_gb=100,
+                    gpu=1,
                 ),
             ),
             task_scheduling=TaskScheduling(
                 scheduling_oneoff=OneOffScheduling(
-                    trigger_timestamp=int(datetime.now().timestamp()) + 60,
+                    trigger_timestamp=int(datetime.now().timestamp()) + 10,
                     min_replicas=1,
                     max_replicas=10,
                 )
@@ -158,7 +158,7 @@ def create_task_and_start(client, artifact_id):
 
 ### (c) Query the Model Endpoint
 
-Once the task is ready, use the endpoint for inference:
+Once the task is running, use the endpoint for inference:
 
 ```python
 from examples.completion import call_chat_completion
@@ -198,8 +198,8 @@ password: Optional[str] = ""
 ## Notes & Troubleshooting
 
 Ensure Credentials are Correct: Double-check your environment variables or parameters passed into the Client object.
-Artifact Status: It may take a few minutes for an artifact or task to transition to the "ready" state.
-Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "ready".
+Artifact Status: It may take a few minutes for an artifact or task to transition to the "running" state.
+Inference Endpoint Readiness: Use the task endpoint only after the task status changes to "running".
 Default OpenAI Key: By default, the OpenAI API base URL is derived from the endpoint provided by GMI.
 
 ## Contributing

{gmicloud-0.1.1 → gmicloud-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "gmicloud"
-version = "0.1.1"
+version = "0.1.2"
 description = "GMI Cloud Python SDK"
 authors = [{ name = "GMI", email = "gmi@gmitec.net" }]
 license = { text = "MIT" }