gmicloud 0.1.4__tar.gz → 0.1.6__tar.gz

gmicloud-0.1.6/PKG-INFO

@@ -0,0 +1,147 @@
+Metadata-Version: 2.2
+Name: gmicloud
+Version: 0.1.6
+Summary: GMI Cloud Python SDK
+Author-email: GMI <support@gmicloud.ai>
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+
+# GMICloud SDK (Beta)
+
+## Overview
+Before you start: Our service and GPU resource is currenly invite-only so please contact our team (getstarted@gmicloud.ai) to get invited if you don't have one yet.
+
+The GMI Inference Engine SDK provides a Python interface for deploying and managing machine learning models in production environments. It allows users to create model artifacts, schedule tasks for serving models, and call inference APIs easily.
+
+This SDK streamlines the process of utilizing GMI Cloud capabilities such as deploying models with Kubernetes-based Ray services, managing resources automatically, and accessing model inference endpoints. With minimal setup, developers can focus on building ML solutions instead of infrastructure.
+
+## Features
+
+- Artifact Management: Easily create, update, and manage ML model artifacts.
+- Task Management: Quickly create, schedule, and manage deployment tasks for model inference.
+- Usage Data Retrieval : Fetch and analyze usage data to optimize resource allocation.
+
+## Installation
+
+To install the SDK, use pip:
+
+```bash
+pip install gmicloud
+```
+
+## Setup
+
+You must configure authentication credentials for accessing the GMI Cloud API. 
+To create account and get log in info please visit **GMI inference platform: https://inference-engine.gmicloud.ai/**.
+
+There are two ways to configure the SDK:
+
+### Option 1: Using Environment Variables
+
+Set the following environment variables:
+
+```shell
+export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
+export GMI_CLOUD_EMAIL=<YOUR_EMAIL>
+export GMI_CLOUD_PASSWORD=<YOUR_PASSWORD>
+```
+
+### Option 2: Passing Credentials as Parameters
+
+Pass `client_id`, `email`, and `password` directly to the Client object when initializing it in your script:
+
+```python
+from gmicloud import Client
+
+client = Client(client_id="<YOUR_CLIENT_ID>", email="<YOUR_EMAIL>", password="<YOUR_PASSWORD>")
+```
+
+## Quick Start
+
+### 1. How to run the code in the example folder
+```bash
+cd path/to/gmicloud-sdk
+# Create a virtual environment
+python -m venv venv
+source venv/bin/activate
+
+pip install -r requirements.txt
+python -m examples.create_task_from_artifact_template.py
+```
+
+### 2. Create an inference task from an artifact template
+
+This is the simplest example to deploy an inference task using an existing artifact template:
+
+Up-to-date code in /examples/create_task_from_artifact_template.py
+
+```python
+from datetime import datetime
+import os
+import sys
+
+from gmicloud import *
+from examples.completion import call_chat_completion
+
+cli = Client()
+
+# List templates offered by GMI cloud 
+templates = cli.list_templates()
+print(f"Found {len(templates)} templates: {templates}")
+
+# Pick a template from the list
+pick_template = "Llama-3.1-8B"
+
+# Create Artifact from template
+artifact_id, recommended_replica_resources = cli.create_artifact_from_template(templates[0])
+print(f"Created artifact {artifact_id} with recommended replica resources: {recommended_replica_resources}")
+
+# Create Task based on Artifact
+task_id = cli.create_task(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=1,
+    )
+))
+task = cli.task_manager.get_task(task_id)
+print(f"Task created: {task.config.task_name}. You can check details at https://inference-engine.gmicloud.ai/user-console/task")
+
+# Start Task and wait for it to be ready
+cli.start_task_and_wait(task.task_id)
+
+# Testing with calling chat completion
+print(call_chat_completion(cli, task.task_id))
+
+```
+
+## API Reference
+
+### Client
+
+Represents the entry point to interact with GMI Cloud APIs.
+Client(
+client_id: Optional[str] = "",
+email: Optional[str] = "",
+password: Optional[str] = ""
+)
+
+### Artifact Management
+
+* get_artifact_templates(): Fetch a list of available artifact templates.
+* create_artifact_from_template(template_id: str): Create a model artifact from a given template.
+* get_artifact(artifact_id: str): Get details of a specific artifact.
+
+### Task Management
+
+* create_task_from_artifact_template(template_id: str, scheduling: TaskScheduling): Create and schedule a task using an
+  artifact template.
+* start_task(task_id: str): Start a task.
+* get_task(task_id: str): Retrieve the status and details of a specific task.
+
+## Notes & Troubleshooting
+k

gmicloud-0.1.6/README.md

@@ -0,0 +1,135 @@
+# GMICloud SDK (Beta)
+
+## Overview
+Before you start: Our service and GPU resource is currenly invite-only so please contact our team (getstarted@gmicloud.ai) to get invited if you don't have one yet.
+
+The GMI Inference Engine SDK provides a Python interface for deploying and managing machine learning models in production environments. It allows users to create model artifacts, schedule tasks for serving models, and call inference APIs easily.
+
+This SDK streamlines the process of utilizing GMI Cloud capabilities such as deploying models with Kubernetes-based Ray services, managing resources automatically, and accessing model inference endpoints. With minimal setup, developers can focus on building ML solutions instead of infrastructure.
+
+## Features
+
+- Artifact Management: Easily create, update, and manage ML model artifacts.
+- Task Management: Quickly create, schedule, and manage deployment tasks for model inference.
+- Usage Data Retrieval : Fetch and analyze usage data to optimize resource allocation.
+
+## Installation
+
+To install the SDK, use pip:
+
+```bash
+pip install gmicloud
+```
+
+## Setup
+
+You must configure authentication credentials for accessing the GMI Cloud API. 
+To create account and get log in info please visit **GMI inference platform: https://inference-engine.gmicloud.ai/**.
+
+There are two ways to configure the SDK:
+
+### Option 1: Using Environment Variables
+
+Set the following environment variables:
+
+```shell
+export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
+export GMI_CLOUD_EMAIL=<YOUR_EMAIL>
+export GMI_CLOUD_PASSWORD=<YOUR_PASSWORD>
+```
+
+### Option 2: Passing Credentials as Parameters
+
+Pass `client_id`, `email`, and `password` directly to the Client object when initializing it in your script:
+
+```python
+from gmicloud import Client
+
+client = Client(client_id="<YOUR_CLIENT_ID>", email="<YOUR_EMAIL>", password="<YOUR_PASSWORD>")
+```
+
+## Quick Start
+
+### 1. How to run the code in the example folder
+```bash
+cd path/to/gmicloud-sdk
+# Create a virtual environment
+python -m venv venv
+source venv/bin/activate
+
+pip install -r requirements.txt
+python -m examples.create_task_from_artifact_template.py
+```
+
+### 2. Create an inference task from an artifact template
+
+This is the simplest example to deploy an inference task using an existing artifact template:
+
+Up-to-date code in /examples/create_task_from_artifact_template.py
+
+```python
+from datetime import datetime
+import os
+import sys
+
+from gmicloud import *
+from examples.completion import call_chat_completion
+
+cli = Client()
+
+# List templates offered by GMI cloud 
+templates = cli.list_templates()
+print(f"Found {len(templates)} templates: {templates}")
+
+# Pick a template from the list
+pick_template = "Llama-3.1-8B"
+
+# Create Artifact from template
+artifact_id, recommended_replica_resources = cli.create_artifact_from_template(templates[0])
+print(f"Created artifact {artifact_id} with recommended replica resources: {recommended_replica_resources}")
+
+# Create Task based on Artifact
+task_id = cli.create_task(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=1,
+    )
+))
+task = cli.task_manager.get_task(task_id)
+print(f"Task created: {task.config.task_name}. You can check details at https://inference-engine.gmicloud.ai/user-console/task")
+
+# Start Task and wait for it to be ready
+cli.start_task_and_wait(task.task_id)
+
+# Testing with calling chat completion
+print(call_chat_completion(cli, task.task_id))
+
+```
+
+## API Reference
+
+### Client
+
+Represents the entry point to interact with GMI Cloud APIs.
+Client(
+client_id: Optional[str] = "",
+email: Optional[str] = "",
+password: Optional[str] = ""
+)
+
+### Artifact Management
+
+* get_artifact_templates(): Fetch a list of available artifact templates.
+* create_artifact_from_template(template_id: str): Create a model artifact from a given template.
+* get_artifact(artifact_id: str): Get details of a specific artifact.
+
+### Task Management
+
+* create_task_from_artifact_template(template_id: str, scheduling: TaskScheduling): Create and schedule a task using an
+  artifact template.
+* start_task(task_id: str): Start a task.
+* get_task(task_id: str): Retrieve the status and details of a specific task.
+
+## Notes & Troubleshooting
+k

{gmicloud-0.1.4 → gmicloud-0.1.6}/gmicloud/__init__.py

@@ -1,3 +1,6 @@
+import logging
+import os
+
 from ._internal._models import (
     Artifact,
     ArtifactData,
@@ -16,7 +19,8 @@ from ._internal._models import (
 )
 from ._internal._enums import (
     BuildStatus,
-    TaskEndpointStatus
+    TaskEndpointStatus,
+    TaskStatus
 )
 from .client import Client
 
@@ -39,3 +43,10 @@ __all__ = [
     "BuildStatus",
     "TaskEndpointStatus",
 ]
+
+# Configure logging
+log_level = os.getenv("GMI_CLOUD_LOG_LEVEL", "INFO").upper()
+logging.basicConfig(
+    level=log_level,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)

gmicloud-0.1.6/gmicloud/_internal/_client/_artifact_client.py

@@ -0,0 +1,212 @@
+from typing import List
+import logging
+from requests.exceptions import RequestException
+
+from ._http_client import HTTPClient
+from ._iam_client import IAMClient
+from ._decorator import handle_refresh_token
+from .._models import *
+from .._config import ARTIFACT_SERVICE_BASE_URL
+
+logger = logging.getLogger(__name__)
+
+
+class ArtifactClient:
+    """
+    Client for interacting with the Artifact Service API.
+
+    This client provides methods to perform CRUD operations on artifacts,
+    as well as generating signed URLs for uploading large files.
+    """
+
+    def __init__(self, iam_client: IAMClient):
+        """
+        Initializes the ArtifactClient with an HTTPClient configured
+        to communicate with the Artifact Service base URL.
+        """
+        self.client = HTTPClient(ARTIFACT_SERVICE_BASE_URL)
+        self.iam_client = iam_client
+
+    @handle_refresh_token
+    def get_artifact(self, artifact_id: str) -> Optional[Artifact]:
+        """
+        Fetches an artifact by its ID.
+
+        :param artifact_id: The ID of the artifact to fetch.
+        :return: The Artifact object or None if an error occurs.
+        """
+        try:
+            response = self.client.get(
+                "/get_artifact",
+                self.iam_client.get_custom_headers(),
+                {"artifact_id": artifact_id}
+            )
+            return Artifact.model_validate(response) if response else None
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to fetch artifact {artifact_id}: {e}")
+            return None
+
+    @handle_refresh_token
+    def get_all_artifacts(self) -> List[Artifact]:
+        """
+        Fetches all artifacts.
+
+        :return: A list of Artifact objects. If an error occurs, returns an empty list.
+        """
+        try:
+            response = self.client.get("/get_all_artifacts", self.iam_client.get_custom_headers())
+            if not response:
+                logger.error("Empty response from /get_all_artifacts")
+                return []
+            return [Artifact.model_validate(item) for item in response]
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to fetch all artifacts: {e}")
+            return []
+
+    @handle_refresh_token
+    def create_artifact(self, request: CreateArtifactRequest) -> Optional[CreateArtifactResponse]:
+        """
+        Creates a new artifact in the service.
+
+        :param request: The request object containing artifact details.
+        :return: The response object containing the created artifact details, or None on error.
+        """
+        try:
+            response = self.client.post(
+                "/create_artifact",
+                self.iam_client.get_custom_headers(),
+                request.model_dump()
+            )
+            return CreateArtifactResponse.model_validate(response) if response else None
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to create artifact: {e}")
+            return None
+
+    @handle_refresh_token
+    def create_artifact_from_template(self, artifact_template_id: str) -> Optional[CreateArtifactFromTemplateResponse]:
+        """
+        Creates a new artifact in the service.
+
+        :param artifact_template_id: The ID of the artifact template to use.
+        :return: The response object containing the created artifact details or None if an error occurs.
+        """
+        try:
+            response = self.client.post(
+                "/create_artifact_from_template",
+                self.iam_client.get_custom_headers(),
+                {"artifact_template_id": artifact_template_id}
+            )
+            return CreateArtifactFromTemplateResponse.model_validate(response) if response else None
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to create artifact from template {artifact_template_id}: {e}")
+            return None
+
+    @handle_refresh_token
+    def rebuild_artifact(self, artifact_id: str) -> Optional[RebuildArtifactResponse]:
+        """
+        Rebuilds an artifact in the service.
+
+        :param artifact_id: The ID of the artifact to rebuild.
+        :return: The response object containing the rebuilt artifact details or None if an error occurs.
+        """
+        try:
+            response = self.client.post(
+                "/rebuild_artifact",
+                self.iam_client.get_custom_headers(),
+                {"artifact_id": artifact_id}
+            )
+            return RebuildArtifactResponse.model_validate(response) if response else None
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to rebuild artifact {artifact_id}: {e}")
+            return None
+
+    @handle_refresh_token
+    def delete_artifact(self, artifact_id: str) -> Optional[DeleteArtifactResponse]:
+        """
+        Deletes an artifact by its ID.
+
+        :param artifact_id: The ID of the artifact to delete.
+        :return: The response object containing the deleted artifact details or None if an error occurs.
+        """
+        try:
+            response = self.client.delete(
+                "/delete_artifact",
+                self.iam_client.get_custom_headers(),
+                {"artifact_id": artifact_id}
+            )
+            return DeleteArtifactResponse.model_validate(response) if response else None
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to delete artifact {artifact_id}: {e}")
+            return None
+
+    @handle_refresh_token
+    def get_bigfile_upload_url(self, request: GetBigFileUploadUrlRequest) -> Optional[GetBigFileUploadUrlResponse]:
+        """
+        Generates a pre-signed URL for uploading a large file.
+
+        :param request: The request object containing the artifact ID, file name, and file type.
+        :return: The response object containing the pre-signed URL and upload details, or None if an error occurs.
+        """
+        try:
+            response = self.client.post("/get_bigfile_upload_url",
+                                        self.iam_client.get_custom_headers(),
+                                        request.model_dump())
+
+            if not response:
+                logger.error("Empty response from /get_bigfile_upload_url")
+                return None
+
+            return GetBigFileUploadUrlResponse.model_validate(response)
+
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to generate upload URL: {e}")
+            return None
+
+    @handle_refresh_token
+    def delete_bigfile(self, request: DeleteBigfileRequest) -> Optional[DeleteBigfileResponse]:
+        """
+        Deletes a large file associated with an artifact.
+
+        :param request: The request object containing the artifact ID and file name.
+        :return: The response object containing the deletion status, or None if an error occurs.
+        """
+        try:
+            response = self.client.delete("/delete_bigfile",
+                                          self.iam_client.get_custom_headers(),
+                                          request.model_dump())
+
+            if not response:
+                logger.error("Empty response from /delete_bigfile")
+                return None
+
+            return DeleteBigfileResponse.model_validate(response)
+
+        except (RequestException, ValueError) as e:
+            logger.error(f"Failed to delete big file: {e}")
+            return None
+
+    @handle_refresh_token
+    def get_public_templates(self) -> List[ArtifactTemplate]:
+        """
+        Fetches all artifact templates.
+
+        :return: A list of ArtifactTemplate objects.
+        :rtype: List[ArtifactTemplate]
+        """
+        try:
+            response = self.client.get("/get_public_templates", self.iam_client.get_custom_headers())
+
+            if not response:
+                logger.error("Empty response received from /get_public_templates API")
+                return []
+
+            try:
+                result = GetPublicTemplatesResponse.model_validate(response)
+                return result.artifact_templates
+            except ValueError as ve:
+                logger.error(f"Failed to validate response data: {ve}")
+                return []
+
+        except RequestException as e:
+            logger.error(f"Request to /get_public_templates failed: {e}")
+            return []

{gmicloud-0.1.4 → gmicloud-0.1.6}/gmicloud/_internal/_client/_http_client.py

@@ -1,8 +1,12 @@
+import logging
+
 import requests
 from .._exceptions import APIError
 from .._exceptions import UnauthorizedError
 from .._constants import *
 
+logger = logging.getLogger(__name__)
+
 
 class HTTPClient:
     """
@@ -51,6 +55,7 @@ class HTTPClient:
         response = None
         try:
             response = requests.request(method, url, params=params, json=data, headers=headers)
+            logger.debug(response.text)
             if response.status_code == 401:
                 raise UnauthorizedError("Access token expired or invalid.")
             elif response.status_code != 200 and response.status_code != 201:
@@ -61,7 +66,6 @@ class HTTPClient:
                 raise APIError(f"HTTP Request failed: {error_message}")
             # Raise for HTTP errors
             response.raise_for_status()
-            print(response.text)
 
         except requests.exceptions.RequestException as e:
             raise APIError(f"HTTP Request failed: {str(e)}")