mlops-python-sdk 1.0.0__tar.gz → 1.0.2__tar.gz

mlops_python_sdk-1.0.2/PKG-INFO

@@ -0,0 +1,254 @@
+Metadata-Version: 2.3
+Name: mlops-python-sdk
+Version: 1.0.2
+Summary: MLOps Python SDK for XCloud Service API
+License: MIT
+Author: mlops
+Author-email: mlops@example.com
+Requires-Python: >=3.9,<4.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: attrs (>=23.2.0)
+Requires-Dist: httpx (>=0.27.0,<1.0.0)
+Requires-Dist: packaging (>=24.1)
+Requires-Dist: python-dateutil (>=2.8.2)
+Requires-Dist: typing-extensions (>=4.1.0)
+Project-URL: Bug Tracker, https://github.com/xcloud-service/xservice/issues
+Project-URL: Homepage, https://mlops.cloud/
+Project-URL: Repository, https://github.com/xcloud-service/xservice
+Description-Content-Type: text/markdown
+
+# SDK
+
+Software Development Kits for integrating with the XCloud Service API.
+
+> [!NOTE] SDK Support
+> SDKs provide type-safe, high-level interfaces for interacting with the platform API. They handle authentication, error handling, and request retries automatically.
+
+## Available SDKs
+
+### Python SDK
+
+### Installation
+
+The Python SDK installation.
+
+```bash
+pip install mlops-python-sdk
+```
+
+### Configuration
+
+The SDK reads configuration from environment variables by default:
+
+- `MLOPS_API_KEY`: API key (required)
+- `MLOPS_DOMAIN`: API domain, e.g. `localhost:8090` or `https://example.com`
+- `MLOPS_API_PATH`: API path prefix (default: `/api/v1`)
+- `MLOPS_DEBUG`: `true|false` (default: `false`)
+
+Or configure in code:
+
+```python
+from mlops import ConnectionConfig, Task
+
+config = ConnectionConfig(
+    api_key="xck_...",
+    domain="https://example.com",
+    api_path="/api/v1",
+    debug=False,
+)
+task = Task(config=config)
+```
+
+### Usage
+
+```python
+from mlops import Task
+from mlops.api.client.models.task_status import TaskStatus
+from pathlib import Path
+
+# Initialize Task client (uses environment variables by default)
+task = Task()
+
+# Submit a task with gpu type
+try:
+    result = task.submit(
+        name="gpu-task-from-sdk",
+        image="/mnt/minio/images/01ai-registry.cn-shanghai.cr.aliyuncs.com+public+llamafactory+0.9.3.sqsh",
+        entry_command="llamafactory-cli train /workspace/config/test_lora.yaml",
+        resources={
+            "partition": "gpu",
+            "nodes": 2,
+            "ntasks": 2,
+            "cpus_per_task": 2,
+            "memory": "4G",
+            "time": "01:00:00",
+            "gres": "gpu:nvidia_a10:1",
+            "qos": "qos_xcloud",
+            },
+        cluster_name="slurm-cn",
+        team_id=1,
+        file_path="your file path", # optional, support for .zip, .tar.gz, .tgz
+    )
+
+    if result is not None:
+        print("==== gpu task submitted successfully ====")
+        job_id = result.job_id
+    else:
+        print("==== gpu task submitted failed ====")
+except Exception as e:
+    print("==== gpu task submitted failed error ====", e)
+
+# Submit a task with cpu type
+try:
+    entry_content = Path("entry.sh").read_text(encoding="utf-8")
+    result = task.submit(
+        name="cpu-task-from-sdk",
+        image="docker://01ai-registry.cn-shanghai.cr.aliyuncs.com/01-ai/xcs/v2/alpine:3.23.0",
+        entry_command=entry_content,
+        resources={
+            "partition": "cpu",
+            "nodes": 1,
+            "ntasks": 1,
+            "cpus_per_task": 1,
+            "memory": "1G",
+            "time": "01:00:00",
+            "qos": "qos_xcloud",
+        },
+        cluster_name="slurm-cn",
+        team_id=1,
+    )
+
+    if result is not None:
+        print("==== cpu task submitted successfully ====")
+        job_id = result.job_id
+    else:
+        print("==== cpu task submitted failed ====")
+except Exception as e:
+    print("==== cpu task submitted failed error ====", e)
+
+# List tasks with filters
+try:
+    completed_tasks = task.list(
+        status=TaskStatus.COMPLETED,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+
+    # Get task details
+    if completed_tasks is not None and len(completed_tasks.tasks) > 0:
+        print("==== completed_tasks number ====", len(completed_tasks.tasks))
+        task_info = task.get(task_id=completed_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task_info ====", task_info)
+    else:
+        print("==== no completed tasks to get details ====")
+except Exception as e:
+    print("==== get task details failed error ====", e)
+
+
+# Cancel a running task
+try:
+    running_tasks = task.list(
+        status=TaskStatus.RUNNING,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+    if running_tasks is not None and len(running_tasks.tasks) > 0:
+        print("==== running_tasks number ====", len(running_tasks.tasks))
+        # Cancel a task
+        result = task.cancel(task_id=running_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task cancelled ====", running_tasks.tasks[0].job_id, result)
+    else:
+        print("==== no running tasks to cancel ====")
+except Exception as e:
+    print("==== cancel running task failed error ====", e)
+
+
+# Delete a task
+try:
+    completed_tasks = task.list(
+        status=TaskStatus.COMPLETED,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+    if completed_tasks is not None and len(completed_tasks.tasks) > 0:
+        print("==== completed_tasks number ====", len(completed_tasks.tasks))
+        # Delete a task
+        result = task.delete(task_id=completed_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task deleted ====", completed_tasks.tasks[0].job_id, result)
+    else:
+        print("==== no completed tasks to delete ====")
+except Exception as e:
+    print("==== delete completed task failed error ====", e)
+```
+
+**Task Management Methods:**
+
+- `submit()` - Submit a new task with container image and entry command
+- `get()` - Get task details by task ID
+- `list()` - List tasks with optional filters (status, cluster_name, team_id, user_id)
+- `cancel()` - Cancel a running task
+- `delete()` - Delete a task record
+
+**Task Status Values:**
+
+```python
+from mlops.api.client.models.task_status import TaskStatus
+
+TaskStatus.PENDING      # Task is pending
+TaskStatus.QUEUED       # Task is queued
+TaskStatus.RUNNING      # Task is running
+TaskStatus.COMPLETED    # Task completed successfully
+TaskStatus.SUCCEEDED    # Task succeeded
+TaskStatus.FAILED       # Task failed
+TaskStatus.CANCELLED    # Task was cancelled
+TaskStatus.CREATED      # Task was created
+```
+
+**Error Handling:**
+
+```python
+from mlops.exceptions import (
+    APIException,
+    AuthenticationException,
+    NotFoundException,
+    RateLimitException,
+    TimeoutException,
+    InvalidArgumentException,
+    NotEnoughSpaceException
+)
+
+try:
+    result = task.submit(name="test", cluster_name="slurm-cn", command="echo hello")
+except AuthenticationException as e:
+    print(f"Authentication failed: {e}")
+except NotFoundException as e:
+    print(f"Resource not found: {e}")
+except APIException as e:
+    print(f"API error: {e}")
+```
+
+> [!TIP] Error Handling
+> SDKs automatically handle common errors and retry failed requests. Check SDK documentation for error handling best practices.
+
+## Features
+
+- Type-safe API clients
+- Automatic authentication
+- Error handling
+- Request retry logic
+- Response validation
+
+## Resources
+
+- [Python SDK Documentation](https://github.com/xcloud-service/xservice/tree/main/client/python-sdk)
+- [API Reference](https://xcloud-service.com/docs/api)
+

mlops_python_sdk-1.0.2/README.md

@@ -0,0 +1,228 @@
+# SDK
+
+Software Development Kits for integrating with the XCloud Service API.
+
+> [!NOTE] SDK Support
+> SDKs provide type-safe, high-level interfaces for interacting with the platform API. They handle authentication, error handling, and request retries automatically.
+
+## Available SDKs
+
+### Python SDK
+
+### Installation
+
+The Python SDK installation.
+
+```bash
+pip install mlops-python-sdk
+```
+
+### Configuration
+
+The SDK reads configuration from environment variables by default:
+
+- `MLOPS_API_KEY`: API key (required)
+- `MLOPS_DOMAIN`: API domain, e.g. `localhost:8090` or `https://example.com`
+- `MLOPS_API_PATH`: API path prefix (default: `/api/v1`)
+- `MLOPS_DEBUG`: `true|false` (default: `false`)
+
+Or configure in code:
+
+```python
+from mlops import ConnectionConfig, Task
+
+config = ConnectionConfig(
+    api_key="xck_...",
+    domain="https://example.com",
+    api_path="/api/v1",
+    debug=False,
+)
+task = Task(config=config)
+```
+
+### Usage
+
+```python
+from mlops import Task
+from mlops.api.client.models.task_status import TaskStatus
+from pathlib import Path
+
+# Initialize Task client (uses environment variables by default)
+task = Task()
+
+# Submit a task with gpu type
+try:
+    result = task.submit(
+        name="gpu-task-from-sdk",
+        image="/mnt/minio/images/01ai-registry.cn-shanghai.cr.aliyuncs.com+public+llamafactory+0.9.3.sqsh",
+        entry_command="llamafactory-cli train /workspace/config/test_lora.yaml",
+        resources={
+            "partition": "gpu",
+            "nodes": 2,
+            "ntasks": 2,
+            "cpus_per_task": 2,
+            "memory": "4G",
+            "time": "01:00:00",
+            "gres": "gpu:nvidia_a10:1",
+            "qos": "qos_xcloud",
+            },
+        cluster_name="slurm-cn",
+        team_id=1,
+        file_path="your file path", # optional, support for .zip, .tar.gz, .tgz
+    )
+
+    if result is not None:
+        print("==== gpu task submitted successfully ====")
+        job_id = result.job_id
+    else:
+        print("==== gpu task submitted failed ====")
+except Exception as e:
+    print("==== gpu task submitted failed error ====", e)
+
+# Submit a task with cpu type
+try:
+    entry_content = Path("entry.sh").read_text(encoding="utf-8")
+    result = task.submit(
+        name="cpu-task-from-sdk",
+        image="docker://01ai-registry.cn-shanghai.cr.aliyuncs.com/01-ai/xcs/v2/alpine:3.23.0",
+        entry_command=entry_content,
+        resources={
+            "partition": "cpu",
+            "nodes": 1,
+            "ntasks": 1,
+            "cpus_per_task": 1,
+            "memory": "1G",
+            "time": "01:00:00",
+            "qos": "qos_xcloud",
+        },
+        cluster_name="slurm-cn",
+        team_id=1,
+    )
+
+    if result is not None:
+        print("==== cpu task submitted successfully ====")
+        job_id = result.job_id
+    else:
+        print("==== cpu task submitted failed ====")
+except Exception as e:
+    print("==== cpu task submitted failed error ====", e)
+
+# List tasks with filters
+try:
+    completed_tasks = task.list(
+        status=TaskStatus.COMPLETED,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+
+    # Get task details
+    if completed_tasks is not None and len(completed_tasks.tasks) > 0:
+        print("==== completed_tasks number ====", len(completed_tasks.tasks))
+        task_info = task.get(task_id=completed_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task_info ====", task_info)
+    else:
+        print("==== no completed tasks to get details ====")
+except Exception as e:
+    print("==== get task details failed error ====", e)
+
+
+# Cancel a running task
+try:
+    running_tasks = task.list(
+        status=TaskStatus.RUNNING,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+    if running_tasks is not None and len(running_tasks.tasks) > 0:
+        print("==== running_tasks number ====", len(running_tasks.tasks))
+        # Cancel a task
+        result = task.cancel(task_id=running_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task cancelled ====", running_tasks.tasks[0].job_id, result)
+    else:
+        print("==== no running tasks to cancel ====")
+except Exception as e:
+    print("==== cancel running task failed error ====", e)
+
+
+# Delete a task
+try:
+    completed_tasks = task.list(
+        status=TaskStatus.COMPLETED,
+        cluster_name="slurm-cn",
+        page=1,
+        page_size=20
+    )
+    if completed_tasks is not None and len(completed_tasks.tasks) > 0:
+        print("==== completed_tasks number ====", len(completed_tasks.tasks))
+        # Delete a task
+        result = task.delete(task_id=completed_tasks.tasks[0].job_id, cluster_name="slurm-cn")
+        print("==== task deleted ====", completed_tasks.tasks[0].job_id, result)
+    else:
+        print("==== no completed tasks to delete ====")
+except Exception as e:
+    print("==== delete completed task failed error ====", e)
+```
+
+**Task Management Methods:**
+
+- `submit()` - Submit a new task with container image and entry command
+- `get()` - Get task details by task ID
+- `list()` - List tasks with optional filters (status, cluster_name, team_id, user_id)
+- `cancel()` - Cancel a running task
+- `delete()` - Delete a task record
+
+**Task Status Values:**
+
+```python
+from mlops.api.client.models.task_status import TaskStatus
+
+TaskStatus.PENDING      # Task is pending
+TaskStatus.QUEUED       # Task is queued
+TaskStatus.RUNNING      # Task is running
+TaskStatus.COMPLETED    # Task completed successfully
+TaskStatus.SUCCEEDED    # Task succeeded
+TaskStatus.FAILED       # Task failed
+TaskStatus.CANCELLED    # Task was cancelled
+TaskStatus.CREATED      # Task was created
+```
+
+**Error Handling:**
+
+```python
+from mlops.exceptions import (
+    APIException,
+    AuthenticationException,
+    NotFoundException,
+    RateLimitException,
+    TimeoutException,
+    InvalidArgumentException,
+    NotEnoughSpaceException
+)
+
+try:
+    result = task.submit(name="test", cluster_name="slurm-cn", command="echo hello")
+except AuthenticationException as e:
+    print(f"Authentication failed: {e}")
+except NotFoundException as e:
+    print(f"Resource not found: {e}")
+except APIException as e:
+    print(f"API error: {e}")
+```
+
+> [!TIP] Error Handling
+> SDKs automatically handle common errors and retry failed requests. Check SDK documentation for error handling best practices.
+
+## Features
+
+- Type-safe API clients
+- Automatic authentication
+- Error handling
+- Request retry logic
+- Response validation
+
+## Resources
+
+- [Python SDK Documentation](https://github.com/xcloud-service/xservice/tree/main/client/python-sdk)
+- [API Reference](https://xcloud-service.com/docs/api)

{mlops_python_sdk-1.0.0 → mlops_python_sdk-1.0.2}/mlops/__init__.py

@@ -1,5 +1,5 @@
 """
-XClient Python SDK for accessing XCloud Service API.
+MLOps Python SDK for accessing MLOps API.
 
 This package provides a client library for interacting with the XCloud Service API.
 """
@@ -10,7 +10,7 @@ from .connection_config import (
     ProxyTypes,
 )
 from .exceptions import (
-    XClientException,
+    MLOpsException,
     TimeoutException,
     NotFoundException,
     AuthenticationException,
@@ -29,7 +29,7 @@ __all__ = [
     "ConnectionConfig",
     "ProxyTypes",
     # Exceptions
-    "XClientException",
+    "MLOpsException",
     "TimeoutException",
     "NotFoundException",
     "AuthenticationException",

mlops_python_sdk-1.0.2/mlops/api/client/api/storage/get_storage_presign_download.py

@@ -0,0 +1,175 @@
+from http import HTTPStatus
+from typing import Any, Optional, Union
+
+import httpx
+
+from ... import errors
+from ...client import AuthenticatedClient, Client
+from ...models.error_response import ErrorResponse
+from ...models.get_storage_presign_download_response_200 import GetStoragePresignDownloadResponse200
+from ...types import UNSET, Response
+
+
+def _get_kwargs(
+    *,
+    key: str,
+) -> dict[str, Any]:
+    params: dict[str, Any] = {}
+
+    params["key"] = key
+
+    params = {k: v for k, v in params.items() if v is not UNSET and v is not None}
+
+    _kwargs: dict[str, Any] = {
+        "method": "get",
+        "url": "/storage/presign_download",
+        "params": params,
+    }
+
+    return _kwargs
+
+
+def _parse_response(
+    *, client: Union[AuthenticatedClient, Client], response: httpx.Response
+) -> Optional[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    if response.status_code == 200:
+        response_200 = GetStoragePresignDownloadResponse200.from_dict(response.json())
+
+        return response_200
+    if response.status_code == 400:
+        response_400 = ErrorResponse.from_dict(response.json())
+
+        return response_400
+    if response.status_code == 500:
+        response_500 = ErrorResponse.from_dict(response.json())
+
+        return response_500
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(
+    *, client: Union[AuthenticatedClient, Client], response: httpx.Response
+) -> Response[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    *,
+    client: AuthenticatedClient,
+    key: str,
+) -> Response[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    """Get presigned URL for file download
+
+     Generates a presigned URL for downloading a file from S3.
+
+    Args:
+        key (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]
+    """
+
+    kwargs = _get_kwargs(
+        key=key,
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+
+def sync(
+    *,
+    client: AuthenticatedClient,
+    key: str,
+) -> Optional[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    """Get presigned URL for file download
+
+     Generates a presigned URL for downloading a file from S3.
+
+    Args:
+        key (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Union[ErrorResponse, GetStoragePresignDownloadResponse200]
+    """
+
+    return sync_detailed(
+        client=client,
+        key=key,
+    ).parsed
+
+
+async def asyncio_detailed(
+    *,
+    client: AuthenticatedClient,
+    key: str,
+) -> Response[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    """Get presigned URL for file download
+
+     Generates a presigned URL for downloading a file from S3.
+
+    Args:
+        key (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]
+    """
+
+    kwargs = _get_kwargs(
+        key=key,
+    )
+
+    response = await client.get_async_httpx_client().request(**kwargs)
+
+    return _build_response(client=client, response=response)
+
+
+async def asyncio(
+    *,
+    client: AuthenticatedClient,
+    key: str,
+) -> Optional[Union[ErrorResponse, GetStoragePresignDownloadResponse200]]:
+    """Get presigned URL for file download
+
+     Generates a presigned URL for downloading a file from S3.
+
+    Args:
+        key (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Union[ErrorResponse, GetStoragePresignDownloadResponse200]
+    """
+
+    return (
+        await asyncio_detailed(
+            client=client,
+            key=key,
+        )
+    ).parsed