mlops-python-sdk 1.0.2__tar.gz → 1.0.4__tar.gz

mlops_python_sdk-1.0.4/PKG-INFO

@@ -0,0 +1,235 @@
+Metadata-Version: 2.3
+Name: mlops-python-sdk
+Version: 1.0.4
+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.
+
+
+## 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)
+```
+
+## SDK Usage
+
+### Initialize client
+
+```python
+from mlops import Task
+
+task = Task()  # uses environment variables by default
+```
+
+### Submit a GPU task
+
+```python
+from mlops import Task
+
+task = Task()
+resp = task.submit(
+    name="gpu-task-from-sdk",
+    cluster_name="slurm-cn",
+    team_id=1,
+    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",
+    },
+    file_path="/path/to/xservice.zip",  # optional: .zip/.tar.gz/.tgz
+)
+print(resp.job_id)
+```
+
+### Submit a CPU task
+
+```python
+from mlops import Task
+
+task = Task()
+resp = task.submit(
+    name="cpu-task-from-sdk",
+    cluster_name="slurm-cn",
+    team_id=1,
+    image="docker://01ai-registry.cn-shanghai.cr.aliyuncs.com/01-ai/xcs/v2/alpine:3.23.0",
+    entry_command="echo hello",
+    resources={
+        "partition": "cpu",
+        "nodes": 1,
+        "ntasks": 1,
+        "cpus_per_task": 1,
+        "memory": "1G",
+        "time": "01:00:00",
+        "qos": "qos_xcloud",
+    },
+)
+print(resp.job_id)
+```
+
+### List tasks
+
+```python
+from mlops import Task
+from mlops.api.client.models.task_status import TaskStatus
+
+task = Task()
+resp = task.list(status=TaskStatus.COMPLETED, cluster_name="slurm-cn", page=1, page_size=20)
+print(len(resp.tasks or []))
+```
+
+### Get task details
+
+```python
+from mlops import Task
+
+task = Task()
+task_info = task.get(task_id=12345, cluster_name="slurm-cn")
+print(task_info)
+```
+
+### Cancel a task
+
+```python
+from mlops import Task
+
+task = Task()
+task.cancel(task_id=12345, cluster_name="slurm-cn")
+```
+
+### Delete a task
+
+```python
+from mlops import Task
+
+task = Task()
+task.delete(task_id=12345, cluster_name="slurm-cn")
+```
+
+**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
+)
+from mlops import Task
+
+task = Task()
+
+try:
+    result = task.submit(
+        name="test",
+        cluster_name="slurm-cn",
+        image="docker://alpine:3.23.0",
+        entry_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 parse typed responses and raise structured exceptions.
+
+## Features
+
+- Type-safe API clients
+- Automatic authentication
+- Error handling
+- Typed response parsing (generated models)
+- Unexpected-status guard (optional)
+
+## 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-1.0.4/README.md

@@ -0,0 +1,209 @@
+# 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.
+
+
+## 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)
+```
+
+## SDK Usage
+
+### Initialize client
+
+```python
+from mlops import Task
+
+task = Task()  # uses environment variables by default
+```
+
+### Submit a GPU task
+
+```python
+from mlops import Task
+
+task = Task()
+resp = task.submit(
+    name="gpu-task-from-sdk",
+    cluster_name="slurm-cn",
+    team_id=1,
+    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",
+    },
+    file_path="/path/to/xservice.zip",  # optional: .zip/.tar.gz/.tgz
+)
+print(resp.job_id)
+```
+
+### Submit a CPU task
+
+```python
+from mlops import Task
+
+task = Task()
+resp = task.submit(
+    name="cpu-task-from-sdk",
+    cluster_name="slurm-cn",
+    team_id=1,
+    image="docker://01ai-registry.cn-shanghai.cr.aliyuncs.com/01-ai/xcs/v2/alpine:3.23.0",
+    entry_command="echo hello",
+    resources={
+        "partition": "cpu",
+        "nodes": 1,
+        "ntasks": 1,
+        "cpus_per_task": 1,
+        "memory": "1G",
+        "time": "01:00:00",
+        "qos": "qos_xcloud",
+    },
+)
+print(resp.job_id)
+```
+
+### List tasks
+
+```python
+from mlops import Task
+from mlops.api.client.models.task_status import TaskStatus
+
+task = Task()
+resp = task.list(status=TaskStatus.COMPLETED, cluster_name="slurm-cn", page=1, page_size=20)
+print(len(resp.tasks or []))
+```
+
+### Get task details
+
+```python
+from mlops import Task
+
+task = Task()
+task_info = task.get(task_id=12345, cluster_name="slurm-cn")
+print(task_info)
+```
+
+### Cancel a task
+
+```python
+from mlops import Task
+
+task = Task()
+task.cancel(task_id=12345, cluster_name="slurm-cn")
+```
+
+### Delete a task
+
+```python
+from mlops import Task
+
+task = Task()
+task.delete(task_id=12345, cluster_name="slurm-cn")
+```
+
+**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
+)
+from mlops import Task
+
+task = Task()
+
+try:
+    result = task.submit(
+        name="test",
+        cluster_name="slurm-cn",
+        image="docker://alpine:3.23.0",
+        entry_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 parse typed responses and raise structured exceptions.
+
+## Features
+
+- Type-safe API clients
+- Automatic authentication
+- Error handling
+- Typed response parsing (generated models)
+- Unexpected-status guard (optional)
+
+## 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 → mlops_python_sdk-1.0.4}/mlops/connection_config.py

@@ -66,17 +66,7 @@ class ConnectionConfig:
             self.api_path = "/" + self.api_path
 
         # Build API URL
-        if self.debug:
-            base_url = "http://localhost:8090"
-        else:
-            # If domain already includes protocol, use it as-is
-            # Otherwise, default to http:// for backward compatibility
-            if self.domain.startswith(("http://", "https://")):
-                base_url = self.domain
-            else:
-                base_url = f"http://{self.domain}"
-        
-        self.api_url = f"{base_url}{self.api_path}"
+        self.build_api_url()
 
     @staticmethod
     def _get_request_timeout(
@@ -89,7 +79,22 @@ class ConnectionConfig:
             return request_timeout
         else:
             return default_timeout
-
+    
+    def build_api_url(self) -> None:
+        if self.debug:
+            base_url = "http://localhost:8090"
+        else:
+            # If domain already includes protocol, use it as-is
+            # Otherwise, default to http:// for backward compatibility
+            if self.domain.startswith(("http://", "https://")):
+                base_url = self.domain
+            elif self.domain.startswith("localhost") or self.domain.startswith("127.0.0.1"):
+                base_url = f"http://{self.domain}"
+            else:
+                base_url = f"https://{self.domain}"
+        
+        self.api_url = f"{base_url}{self.api_path}"
+        
     def get_request_timeout(self, request_timeout: Optional[float] = None):
         return self._get_request_timeout(self.request_timeout, request_timeout)