mlops-python-sdk 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

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/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"

mlops/task/task.py

@@ -6,6 +6,9 @@ This module provides a convenient interface for managing tasks through the MLOps
 
 import json
 import os
+import sys
+import threading
+import time
 from http import HTTPStatus
 from pathlib import Path
 from typing import Optional
@@ -55,13 +58,109 @@ def _validate_archive_file_path(file_path: str) -> Path:
 
 
 def _upload_file_to_presigned_url(url: str, file_path: Path, timeout: Optional[float]) -> None:
+    def _format_bytes_iec(n: int) -> str:
+        if n < 1024:
+            return f"{n}B"
+        unit = 1024.0
+        suffixes = ["KiB", "MiB", "GiB", "TiB", "PiB"]
+        v = float(n)
+        i = -1
+        while v >= unit and i < len(suffixes) - 1:
+            v /= unit
+            i += 1
+        return f"{v:.1f}{suffixes[i]}"
+
+    def _render_bar(done: int, total: int, width: int = 28) -> str:
+        if total <= 0 or width <= 1:
+            return ">"
+        done = max(0, min(done, total))
+        filled = int(width * (done / total))
+        if filled >= width:
+            return "=" * width
+        if filled <= 0:
+            return ">" + (" " * (width - 1))
+        return ("=" * filled) + ">" + (" " * (width - filled - 1))
+
+    def _format_elapsed_seconds(start: float) -> str:
+        sec = int(max(0.0, time.monotonic() - start))
+        return f"{sec}s"
+
+    class _ProgressIterable:
+        def __init__(self, f, total: int, name: str, chunk_size: int = 64 * 1024):
+            self._f = f  # file-like object
+            self._total = max(0, int(total))
+            self._name = name
+            self._chunk_size = max(1, int(chunk_size))
+            self._read = 0
+            self._start = time.monotonic()
+            self._completed = False
+            self._out = sys.stdout
+            try:
+                self._is_tty = bool(self._out.isatty())
+            except Exception:
+                self._is_tty = False
+
+        def _render_line(self, display_read: int) -> str:
+            display_read = max(0, min(int(display_read), self._total))
+            pct = (display_read / self._total) * 100.0 if self._total > 0 else 0.0
+            bar = _render_bar(display_read, self._total, width=28)
+            elapsed = _format_elapsed_seconds(self._start)
+            return (
+                f"uploading {self._name} [{bar}] {pct:6.2f}% "
+                f"({_format_bytes_iec(display_read)}/{_format_bytes_iec(self._total)}) "
+                f"elapsed {elapsed}"
+            )
+
+        def _print_line(self, line: str, final: bool = False) -> None:
+            if self._is_tty:
+                # Refresh same line in terminal.
+                print("\r" + line, end="" if not final else "\n", file=self._out, flush=True)
+            else:
+                # Always visible in non-TTY environments.
+                print(line, file=self._out, flush=True)
+
+        def __iter__(self):
+            stop_event = threading.Event()
+
+            def ticker() -> None:
+                last_sec = -1
+                # Print immediately so users see something right away.
+                self._print_line(self._render_line(self._read))
+                while not stop_event.is_set():
+                    sec = int(max(0.0, time.monotonic() - self._start))
+                    if sec != last_sec:
+                        last_sec = sec
+                        self._print_line(self._render_line(self._read))
+                    # check frequently to avoid skipping seconds
+                    stop_event.wait(0.05)
+
+            t = threading.Thread(target=ticker, name="mlops-upload-progress", daemon=True)
+            t.start()
+            try:
+                while True:
+                    chunk = self._f.read(self._chunk_size)
+                    if not chunk:
+                        break
+                    self._read += len(chunk)
+                    yield chunk
+            finally:
+                # Ensure a final 100% line and stop ticker.
+                self._read = self._total
+                self._completed = True
+                stop_event.set()
+                t.join(timeout=0.2)
+                self._print_line(self._render_line(self._read), final=True)
+
     size = file_path.stat().st_size
     # Use a dedicated client for S3 presigned upload (avoid leaking API auth headers).
     with httpx.Client(timeout=timeout) as client:
         with file_path.open("rb") as f:
+            content = f
+            if size > 0:
+                content = _ProgressIterable(f, total=size, name=file_path.name)
             resp = client.put(
                 url,
-                content=f,
+                content=content,
                 headers={
                     "Content-Length": str(size),
                     "Content-Type": "application/octet-stream",
@@ -85,18 +184,25 @@ class Task:
         config = ConnectionConfig(api_key="your_api_key")
         task = Task(config=config)
         
-        # Submit a task with script
-        result = task.submit(
-            name="my-task",
-            cluster_name="slurm-cn",
-            script="#!/bin/bash\\necho 'Hello World'"
-        )
-        
-        # Or submit with command
+        # Submit a task with gpu type
         result = task.submit(
-            name="my-task",
+            name="gpu-task-from-sdk",
             cluster_name="slurm-cn",
-            command="echo 'Hello World'"
+            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",
+                "job_type": "batch",
+            },
+            team_id=1,
+            file_path="your file path",
         )
         
         # Get task details
@@ -151,8 +257,8 @@ class Task:
         self,
         name: str,
         cluster_name: str,
-        script: Optional[str] = None,
-        command: Optional[str] = None,
+        image: str,
+        entry_command: str,
         resources: Optional[dict] = None,
         team_id: Optional[int] = None,
         file_path: Optional[str] = None,
@@ -163,11 +269,11 @@ class Task:
         Args:
             name: Task name
             cluster_name: Cluster name to submit the task to
-            script: Task script content (optional, but at least one of script or command is required)
-            command: Command to execute (optional, but at least one of script or command is required)
+            image: Container image reference
+            entry_command: Container entry command/script
             resources: Resource requirements dict (optional)
             team_id: Team ID (optional)
-
+            file_path: Local file path to upload (optional, support for .zip, .tar.gz, .tgz)
         Returns:
             TaskSubmitResponse containing the submitted task information
 
@@ -175,25 +281,14 @@ class Task:
             APIException: If the API returns an error
             AuthenticationException: If authentication fails
         """
-        # At least one of script or command must be provided
-        if not script and not command:
-            raise APIException("At least one of 'script' or 'command' must be provided")
-        
-        # Map resources dict to individual fields
-        # resources dict can contain: cpu, cpus_per_task, memory, nodes, gres, time, partition, etc.
-
         request_kwargs = {
             "name": name,
             "cluster_name": cluster_name,
+            "image": image,
+            "entry_command": entry_command,
         }
-        
-        # Handle script and command (at least one is required)
-        # script is Union[Unset, str], so we need to set it or leave as UNSET
-        if script:
-            request_kwargs["script"] = script
-        # command is Union[None, Unset, str], so we can set it or leave as UNSET
-        if command:
-            request_kwargs["command"] = command
+        # Map resources dict to individual fields
+        # resources dict can contain: cpu, cpus_per_task, memory, nodes, gres, time, partition, etc.
         
         # team_id is Union[None, Unset, int]
         if team_id is not None:
@@ -203,18 +298,34 @@ class Task:
         if resources:
             if "cpu" in resources or "cpus_per_task" in resources:
                 request_kwargs["cpus_per_task"] = resources.get("cpus_per_task") or resources.get("cpu")
+            else:
+                request_kwargs["cpus_per_task"] = 1
             if "memory" in resources:
                 request_kwargs["memory"] = resources.get("memory")
+            else: 
+                request_kwargs["memory"] = "1G"
             if "nodes" in resources:
                 request_kwargs["nodes"] = resources.get("nodes")
+            else:
+                request_kwargs["nodes"] = 1
             if "gres" in resources:
                 request_kwargs["gres"] = resources.get("gres")
             if "time" in resources:
                 request_kwargs["time"] = resources.get("time")
+            else:
+                request_kwargs["time"] = "01:00:00"
             if "partition" in resources:
                 request_kwargs["partition"] = resources.get("partition")
-            if "tres" in resources:
-                request_kwargs["tres"] = resources.get("tres")
+            else:
+                request_kwargs["partition"] = "debug"
+            if "qos" in resources:
+                request_kwargs["qos"] = resources.get("qos")
+            else:
+                request_kwargs["qos"] = "qos_xcloud"
+            if "ntasks" in resources:
+                request_kwargs["ntasks"] = resources.get("ntasks")
+            else:
+                request_kwargs["ntasks"] = 1
 
         if file_path:
             local_path = _validate_archive_file_path(file_path)

mlops_python_sdk-1.0.3.dist-info/METADATA

@@ -0,0 +1,235 @@
+Metadata-Version: 2.3
+Name: mlops-python-sdk
+Version: 1.0.3
+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-1.0.1.dist-info → mlops_python_sdk-1.0.3.dist-info}/RECORD

@@ -35,18 +35,18 @@ mlops/api/client/models/task_log_entry_log_type.py,sha256=uVqbF8RewyFkezY6sy28He
 mlops/api/client/models/task_logs_response.py,sha256=QEGRy51qB7t0K-EGusxzDmkDlAjdKkwHF92em3dLb1c,3557
 mlops/api/client/models/task_resources_type_0.py,sha256=36nxeOqAJS4ksfQtzoXigWVMhEV1Tnq5Z_64sHa3gGQ,1341
 mlops/api/client/models/task_status.py,sha256=Tht4F2UeBp-QBLhh-z0fEw45r5cBCfkFUro-la42BPY,315
-mlops/api/client/models/task_submit_request.py,sha256=8zbEK2Y_dT4S6Wflm6WTNn9f_f-SLQ7Sl92bS2H_T0c,22941
+mlops/api/client/models/task_submit_request.py,sha256=g8THqxUjn0VD4fw8eo6I6qe9Eym6q9vmSSTFrhcUlbc,24803
 mlops/api/client/models/task_submit_request_environment_type_0.py,sha256=Wx6ye6vVHytSex186AeUm27-XMWMmZe6lbL2Ons2mkw,1454
 mlops/api/client/models/task_submit_response.py,sha256=EK3ZXxo_XO5Yn2zdOrR-VMPKg9om49qQ1ywS2Smgink,2200
 mlops/api/client/models/task_tres_type_0.py,sha256=rEaiQG7A19mlTIHDppzxuWa4oPfh9qsKjPhhVOlBf4g,1292
 mlops/api/client/models/task_tres_used_type_0.py,sha256=4w6An7-ZCqa8cc3SPi7mcwGK-ekT6AYq_dEdf8KzoYA,1320
 mlops/api/client/py.typed,sha256=8ZJUsxZiuOy1oJeVhsTWQhTG_6pTVHVXk5hJL79ebTk,25
 mlops/api/client/types.py,sha256=AX4orxQZQJat3vZrgjJ-TYb2sNBL8kNo9yqYDT-n8y8,1391
-mlops/connection_config.py,sha256=aU_8WwkMcomjt4dDyRk1Oyr92ywwuIhFLmv0oQ29KkM,2953
+mlops/connection_config.py,sha256=_b9sVFGJtf1GynmIB4NtKCzg7kkgE-wSrsG3LwzlOqk,2946
 mlops/exceptions.py,sha256=3kfda-Rz0km9kV-gvnPCw7ueemWkXIGGdT0NXx6z9Xk,1680
 mlops/task/__init__.py,sha256=M983vMPLj3tZQNFXQyTP5I2RsRorFElezLeppr3WLsw,133
 mlops/task/client.py,sha256=V131WLVJl1raGAVixUhJCX8s1neN15mxAjQwO01qlIg,3552
-mlops/task/task.py,sha256=7QBSNpmI4jacWep2FaSZyA86wgsx-BiNAlBrKi-Razg,23450
-mlops_python_sdk-1.0.1.dist-info/METADATA,sha256=afpVJjsJ-TN-lmCym3ScsMJhrOdFoId06MBfLEfFbY4,9525
-mlops_python_sdk-1.0.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-mlops_python_sdk-1.0.1.dist-info/RECORD,,
+mlops/task/task.py,sha256=Eqb4XGMlFLjelg3js9Twoulf0Nlyn0pz5isuGl916vs,27756
+mlops_python_sdk-1.0.3.dist-info/METADATA,sha256=KwMwLVAYfXBjKXXiU_p5TibVXGbli5gaxCCa0Wap9h4,5679
+mlops_python_sdk-1.0.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+mlops_python_sdk-1.0.3.dist-info/RECORD,,

mlops_python_sdk-1.0.1.dist-info/METADATA

@@ -1,407 +0,0 @@
-Metadata-Version: 2.3
-Name: mlops-python-sdk
-Version: 1.0.1
-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
-
-# MLOps Python SDK
-
-[MLOps](https://xcloud-service.com) Python SDK for XCloud Service API. Manage and execute tasks with confidence.
-
-## Installation
-
-Install the SDK from PyPI:
-
-```bash
-pip install mlops-python-sdk
-```
-
-## Quick Start
-
-### 1. Setup Authentication
-
-You can authenticate using either an API Key.
-
-#### API Key (Recommended for programmatic access)
-
-1. Sign up at [MLOps](https://xcloud-service.com)
-2. Create an API key from [API Keys](https://xcloud-service.com/home/api-keys)
-3. Set environment variables:
-
-```bash
-export MLOPS_API_KEY=xck_******
-export MLOPS_DOMAIN=localhost:8090  # optional, default is localhost:8090
-```
-
-### 2. Basic Usage
-
-```python
-from mlops import Task, ConnectionConfig
-from mlops.api.client.models.task_status import TaskStatus
-
-# Initialize Task client (uses environment variables by default)
-task = Task()
-
-# Or initialize with explicit configuration
-config = ConnectionConfig(
-    api_key="xck_******",
-    domain="localhost:8090",
-    debug=False
-)
-task = Task(config=config)
-
-# Submit a task with script
-result = task.submit(
-    name="my-training-task",
-    cluster_id=1,
-    script="#!/bin/bash\necho 'Hello World'",
-    resources={"cpu": 4, "memory": "8GB", "gpu": 1}
-)
-
-# Or submit with command
-result = task.submit(
-    name="my-task",
-    cluster_id=1,
-    command="python train.py",
-    resources={"cpu": 4, "memory": "8GB"}
-)
-
-# Get task details
-task_info = task.get(task_id=result.job_id, cluster_id=1)
-
-# List tasks with filters
-running_tasks = task.list(
-    status=TaskStatus.RUNNING,
-    cluster_id=1,
-    page=1,
-    page_size=20
-)
-
-# Cancel a task
-task.cancel(task_id=result.job_id, cluster_id=1)
-
-# Delete a task
-task.delete(task_id=task_id, cluster_id=1)
-```
-
-## API Reference
-
-### Task Class
-
-The `Task` class provides a high-level interface for managing tasks.
-
-#### Initialization
-
-```python
-from mlops import Task, ConnectionConfig
-
-# Using environment variables
-task = Task()
-
-# With explicit configuration
-config = ConnectionConfig(
-    api_key="xck_******",           # API key for authentication
-    domain="localhost:8090",         # API domain
-    debug=False,                      # Enable debug mode
-    request_timeout=30.0              # Request timeout in seconds
-)
-task = Task(config=config)
-
-# Or pass parameters directly
-task = Task(
-    api_key="xck_******",
-    domain="localhost:8090"
-)
-```
-
-#### Methods
-
-##### `submit()`
-
-Submit a new task to the cluster.
-
-```python
-result = task.submit(
-    name: str,                    # Task name (required)
-    cluster_id: int,              # Cluster ID (required)
-    script: Optional[str] = None, # Script content (script or command required)
-    command: Optional[str] = None,# Command to execute (script or command required)
-    resources: Optional[dict] = None, # Resource requirements
-    team_id: Optional[int] = None # Team ID (optional)
-) -> TaskSubmitResponse
-```
-
-**Resources dictionary** can contain:
-- `cpu` or `cpus_per_task`: Number of CPUs
-- `memory`: Memory requirement (e.g., "8GB", "4096M")
-- `nodes`: Number of nodes
-- `gres`: GPU resources (e.g., "gpu:1")
-- `time`: Time limit (e.g., "1-00:00:00" for 1 day)
-- `partition`: Partition name
-- `tres`: TRES specification
-
-**Example:**
-
-```python
-result = task.submit(
-    name="ml-training",
-    cluster_id=1,
-    script="#!/bin/bash\npython train.py --epochs 100",
-    resources={
-        "cpu": 8,
-        "memory": "16GB",
-        "gpu": 1,
-        "time": "2-00:00:00",  # 2 days
-        "partition": "gpu"
-    }
-)
-print(f"Task submitted: Job ID = {result.job_id}")
-```
-
-##### `get()`
-
-Get task details by task ID.
-
-```python
-task_info = task.get(
-    task_id: int,    # Task ID (Slurm job ID)
-    cluster_id: int  # Cluster ID (required)
-) -> Task
-```
-
-**Example:**
-
-```python
-task_info = task.get(task_id=12345, cluster_id=1)
-print(f"Task status: {task_info.status}")
-print(f"Task name: {task_info.name}")
-```
-
-##### `list()`
-
-List tasks with optional filters and pagination.
-
-```python
-tasks = task.list(
-    page: int = 1,                           # Page number
-    page_size: int = 20,                     # Items per page
-    status: Optional[TaskStatus] = None,     # Filter by status
-    cluster_id: Optional[int] = None,         # Filter by cluster ID
-    team_id: Optional[int] = None,           # Filter by team ID
-    user_id: Optional[int] = None            # Filter by user ID
-) -> TaskListResponse
-```
-
-**Example:**
-
-```python
-from mlops.api.client.models.task_status import TaskStatus
-
-# List all running tasks
-running_tasks = task.list(status=TaskStatus.RUNNING)
-
-# List tasks in a specific cluster
-cluster_tasks = task.list(cluster_id=1, page=1, page_size=10)
-
-# List completed tasks with pagination
-completed = task.list(
-    status=TaskStatus.COMPLETED,
-    cluster_id=1,
-    page=1,
-    page_size=50
-)
-```
-
-##### `cancel()`
-
-Cancel a running task.
-
-```python
-task.cancel(
-    task_id: int,    # Task ID (Slurm job ID)
-    cluster_id: int  # Cluster ID (required)
-)
-```
-
-**Example:**
-
-```python
-task.cancel(task_id=12345, cluster_id=1)
-```
-
-### TaskStatus Enum
-
-Task status values for filtering:
-
-```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
-```
-
-## Configuration
-
-### Environment Variables
-
-The SDK reads configuration from environment variables:
-
-- `MLOPS_API_KEY`: API key for authentication
-- `MLOPS_DOMAIN`: API domain (default: `localhost:8090`)
-- `MLOPS_DEBUG`: Enable debug mode (`true`/`false`, default: `false`)
-- `MLOPS_API_PATH`: API path prefix (default: `/api/v1`)
-
-### ConnectionConfig
-
-You can also configure the connection programmatically:
-
-```python
-from mlops import ConnectionConfig
-
-config = ConnectionConfig(
-    domain="api.example.com",
-    api_key="xck_******",
-    debug=True,
-    request_timeout=60.0,
-    api_path="/api/v1"
-)
-```
-
-## Error Handling
-
-The SDK provides specific exception types:
-
-```python
-from mlops.exceptions import (
-    APIException,           # General API errors
-    AuthenticationException, # Authentication failures
-    NotFoundException,       # Resource not found
-    RateLimitException,     # Rate limit exceeded
-    TimeoutException,       # Request timeout
-    InvalidArgumentException # Invalid arguments
-)
-
-try:
-    result = task.submit(name="test", cluster_id=1, 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}")
-```
-
-## Examples
-
-### Submit a Machine Learning Training Job
-
-```python
-from mlops import Task
-
-task = Task()
-
-result = task.submit(
-    name="pytorch-training",
-    cluster_id=1,
-    script="""#!/bin/bash
-#SBATCH --gres=gpu:1
-#SBATCH --cpus-per-task=2
-#SBATCH --mem=4GB
-
-python train.py --config config.yaml
-""",
-    resources={
-        "cpus_per_task": 2,
-        "memory": "4GB",
-        "gres": "gpu:1",
-        "time": "1-00:00:00",  # 1 days
-        "partition": "gpu"
-    }
-)
-
-print(f"Training job submitted: {result.job_id}")
-```
-
-### Monitor Task Status
-
-```python
-from mlops import Task
-from mlops.api.client.models.task_status import TaskStatus
-import time
-
-task = Task()
-job_id = 12345
-cluster_id = 1
-
-while True:
-    task_info = task.get(task_id=job_id, cluster_id=cluster_id)
-    print(f"Status: {task_info.status}")
-    
-    if task_info.status in [TaskStatus.COMPLETED, TaskStatus.FAILED, TaskStatus.CANCELLED]:
-        break
-    
-    time.sleep(10)  # Check every 10 seconds
-```
-
-### List and Filter Tasks
-
-```python
-from mlops import Task
-from mlops.api.client.models.task_status import TaskStatus
-
-task = Task()
-
-# Get all running tasks in cluster 1
-running = task.list(
-    status=TaskStatus.RUNNING,
-    cluster_id=1
-)
-
-for t in running.tasks:
-    print(f"{t.name}: {t.status} (Job ID: {t.job_id})")
-
-# Get failed tasks
-failed = task.list(status=TaskStatus.FAILED)
-
-print(f"Total failed tasks: {failed.total}")
-```
-
-## Documentation
-
-- [MLOPS Documentation](https://xcloud-service.com/docs)
-- [API Reference](https://xcloud-service.com/docs/api)
-
-## License
-
-MIT
-
-## Support
-
-- [GitHub Issues](https://github.com/xcloud-service/xservice/issues)
-- [Documentation](https://xcloud-service.com/docs)
-