mlops-python-sdk 1.0.1__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-1.0.1 → mlops_python_sdk-1.0.2}/mlops/api/client/models/task_submit_request.py

@@ -29,12 +29,18 @@ class TaskSubmitRequest:
         cpus_per_task (Union[None, Unset, int]): CPUs per task Example: 1.
         dependency (Union[None, Unset, str]): Job dependencies Example: afterok:12345.
         distribution (Union[None, Unset, str]): Task distribution Example: block.
+        entry_command (Union[None, Unset, str]): Container entry command/script (bash snippet) executed inside the
+            container. The platform runs it under /workspace.
+             Example: python -V && ls -la.
         environment (Union['TaskSubmitRequestEnvironmentType0', None, Unset]): Environment variables as key-value pairs
             Example: {'CUDA_VISIBLE_DEVICES': '0,1', 'PYTHONPATH': '/opt/python/lib'}.
         error (Union[None, Unset, str]): Standard error file pattern Example: error_%j.log.
         exclude (Union[None, Unset, str]): Nodes to exclude
         export (Union[None, Unset, str]): Environment export Example: ALL.
         gres (Union[None, Unset, str]): Generic resources (e.g., "gpu:1", "gpu:tesla:2") Example: gpu:1.
+        image (Union[None, Unset, str]): Container image reference. Can be a Slurm container plugin supported reference
+            (e.g. "docker://..."), or a registry reference which will be mapped to a local .sqsh image path by the platform.
+             Example: 01ai-registry.cn-shanghai.cr.aliyuncs.com/public/llamafactory:0.9.3.
         input_ (Union[None, Unset, str]): Standard input file
         job_spec (Union[Unset, JobSpec]): Domain-specific job specification (rendered into slurm script)
         mem_bind (Union[None, Unset, str]): Memory binding
@@ -65,11 +71,13 @@ class TaskSubmitRequest:
     cpus_per_task: Union[None, Unset, int] = UNSET
     dependency: Union[None, Unset, str] = UNSET
     distribution: Union[None, Unset, str] = UNSET
+    entry_command: Union[None, Unset, str] = UNSET
     environment: Union["TaskSubmitRequestEnvironmentType0", None, Unset] = UNSET
     error: Union[None, Unset, str] = UNSET
     exclude: Union[None, Unset, str] = UNSET
     export: Union[None, Unset, str] = UNSET
     gres: Union[None, Unset, str] = UNSET
+    image: Union[None, Unset, str] = UNSET
     input_: Union[None, Unset, str] = UNSET
     job_spec: Union[Unset, "JobSpec"] = UNSET
     mem_bind: Union[None, Unset, str] = UNSET
@@ -143,6 +151,12 @@ class TaskSubmitRequest:
         else:
             distribution = self.distribution
 
+        entry_command: Union[None, Unset, str]
+        if isinstance(self.entry_command, Unset):
+            entry_command = UNSET
+        else:
+            entry_command = self.entry_command
+
         environment: Union[None, Unset, dict[str, Any]]
         if isinstance(self.environment, Unset):
             environment = UNSET
@@ -175,6 +189,12 @@ class TaskSubmitRequest:
         else:
             gres = self.gres
 
+        image: Union[None, Unset, str]
+        if isinstance(self.image, Unset):
+            image = UNSET
+        else:
+            image = self.image
+
         input_: Union[None, Unset, str]
         if isinstance(self.input_, Unset):
             input_ = UNSET
@@ -289,6 +309,8 @@ class TaskSubmitRequest:
             field_dict["dependency"] = dependency
         if distribution is not UNSET:
             field_dict["distribution"] = distribution
+        if entry_command is not UNSET:
+            field_dict["entry_command"] = entry_command
         if environment is not UNSET:
             field_dict["environment"] = environment
         if error is not UNSET:
@@ -299,6 +321,8 @@ class TaskSubmitRequest:
             field_dict["export"] = export
         if gres is not UNSET:
             field_dict["gres"] = gres
+        if image is not UNSET:
+            field_dict["image"] = image
         if input_ is not UNSET:
             field_dict["input"] = input_
         if job_spec is not UNSET:
@@ -416,6 +440,15 @@ class TaskSubmitRequest:
 
         distribution = _parse_distribution(d.pop("distribution", UNSET))
 
+        def _parse_entry_command(data: object) -> Union[None, Unset, str]:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            return cast(Union[None, Unset, str], data)
+
+        entry_command = _parse_entry_command(d.pop("entry_command", UNSET))
+
         def _parse_environment(data: object) -> Union["TaskSubmitRequestEnvironmentType0", None, Unset]:
             if data is None:
                 return data
@@ -469,6 +502,15 @@ class TaskSubmitRequest:
 
         gres = _parse_gres(d.pop("gres", UNSET))
 
+        def _parse_image(data: object) -> Union[None, Unset, str]:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            return cast(Union[None, Unset, str], data)
+
+        image = _parse_image(d.pop("image", UNSET))
+
         def _parse_input_(data: object) -> Union[None, Unset, str]:
             if data is None:
                 return data
@@ -615,11 +657,13 @@ class TaskSubmitRequest:
             cpus_per_task=cpus_per_task,
             dependency=dependency,
             distribution=distribution,
+            entry_command=entry_command,
             environment=environment,
             error=error,
             exclude=exclude,
             export=export,
             gres=gres,
+            image=image,
             input_=input_,
             job_spec=job_spec,
             mem_bind=mem_bind,

{mlops_python_sdk-1.0.1 → mlops_python_sdk-1.0.2}/mlops/connection_config.py

@@ -1,9 +1,9 @@
 import os
 
-from typing import Literal, Optional, Dict
+from typing import Optional, Dict
 from httpx._types import ProxyTypes
 
-REQUEST_TIMEOUT: float = 30.0  # 30 seconds
+REQUEST_TIMEOUT: float = 120.0  # 120 seconds
 
 KEEPALIVE_PING_INTERVAL_SEC = 50  # 50 seconds
 KEEPALIVE_PING_HEADER = "Keepalive-Ping-Interval"