gmicloud 0.1.7__tar.gz → 0.1.10__tar.gz

{gmicloud-0.1.7 → gmicloud-0.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gmicloud
-Version: 0.1.7
+Version: 0.1.10
 Summary: GMI Cloud Python SDK
 Author-email: GMI <gmi@gmitec.net>
 License: MIT
@@ -133,7 +133,22 @@ model_checkpoint_save_dir = "files/model_garden"
 snapshot_download(repo_id=model_name, local_dir=model_checkpoint_save_dir)
 ```
 
-2. Find a template of specific SGLang version
+#### Pre-downloaded models
+```
+"deepseek-ai/DeepSeek-R1"
+"deepseek-ai/DeepSeek-V3-0324"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+"meta-llama/Llama-3.3-70B-Instruct"
+"meta-llama/Llama-4-Maverick-17B-128E-Instruct"
+"meta-llama/Llama-4-Scout-17B-16E-Instruct"
+"Qwen/QwQ-32B"
+```
+
+2. Find a template of specific vllm or SGLang version
 
 ```python
 # export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
@@ -158,55 +173,67 @@ picked_template_name = "gmi_sglang_0.4.5.post1"
 serve_command = "python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --trust-remote-code --mem-fraction-static 0.8 --tp 2"
 ```
 
-4. Create an artifact and upload custom model. The artifact can be reused to create inference tasks later. Artifact also suggests recommended resources for each inference server replica
+4. Create an artifact. you can pass `pre_download_model` parameter. If you want custom model, upload model checkpoint to the artifactThe artifact can be reused to create inference tasks later. Artifact also suggests recommended resources for each inference server replica
 
 ```python
-artifact_id, recommended_replica_resources = cli.artifact_manager.create_artifact_from_template_name(
-    artifact_template_name=picked_template_name,
-    env_parameters={
-        "SERVER_COMMAND": serve_command,
-        "GPU_TYPE": "H100",
-    }
+artifact_name = "artifact_hello_world"
+artifact_id, recommended_replica_resources = cli.artifact_manager.create_artifact_for_serve_command_and_custom_model(
+    template_name=picked_template_name,
+    artifact_name=artifact_name,
+    serve_command=serve_command,
+    gpu_type="H100",
+    artifact_description="This is a test artifact",
+    pre_download_model=pick_pre_downloaded_model,
 )
 print(f"Created artifact {artifact_id} with recommended resources: {recommended_replica_resources}")
+```
 
-# Upload model files to artifact
+Alternatively, Upload a custom model checkpoint to artifact
+```python
 cli.artifact_manager.upload_model_files_to_artifact(artifact_id, model_checkpoint_save_dir)
+
+# Maybe Wait 10 minutes for the artifact to be ready
+time.sleep(10 * 60)
 ```
 
 5. Create Inference task (defining min/max inference replica), start and wait
 
 ```python
-new_task = Task(
-    config=TaskConfig(
-        ray_task_config=RayTaskConfig(
-            artifact_id=artifact_id,
-            file_path="serve",
-            deployment_name="app",
-            replica_resource=recommended_replica_resources,
-        ),
-        task_scheduling = TaskScheduling(
-            scheduling_oneoff=OneOffScheduling(
-                trigger_timestamp=int(datetime.now().timestamp()),
-                min_replicas=1,
-                max_replicas=4,
-            )
-        ),
-    ),
-)
-task = cli.task_manager.create_task(new_task)
-task_id = task.task_id
-task = cli.task_manager.get_task(task_id)
+# Create Task based on Artifact
+new_task_id = cli.task_manager.create_task_from_artifact_id(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=4,
+    )
+))
+task = cli.task_manager.get_task(new_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.task_manager.start_task_and_wait(task_id)
+cli.task_manager.start_task_and_wait(new_task_id)
 ```
 
-6. Test with sample chat completion request
+6. Test with sample chat completion request with OpenAI client
 
 ```python
-print(call_chat_completion(cli, task_id))
+pi_key = "<YOUR_API_KEY>"
+endpoint_url = cli.task_manager.get_task_endpoint_url(new_task_id)
+open_ai = OpenAI(
+    base_url=os.getenv("OPENAI_API_BASE", f"https://{endpoint_url}/serve/v1/"),
+    api_key=api_key
+)
+# Make a chat completion request using the new OpenAI client.
+completion = open_ai.chat.completions.create(
+    model=picked_template_name,
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Who are you?"},
+    ],
+    max_tokens=500,
+    temperature=0.7
+)
+print(completion.choices[0].message.content)
 ```
 
 

{gmicloud-0.1.7 → gmicloud-0.1.10}/README.md

@@ -121,7 +121,22 @@ model_checkpoint_save_dir = "files/model_garden"
 snapshot_download(repo_id=model_name, local_dir=model_checkpoint_save_dir)
 ```
 
-2. Find a template of specific SGLang version
+#### Pre-downloaded models
+```
+"deepseek-ai/DeepSeek-R1"
+"deepseek-ai/DeepSeek-V3-0324"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
+"deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
+"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+"meta-llama/Llama-3.3-70B-Instruct"
+"meta-llama/Llama-4-Maverick-17B-128E-Instruct"
+"meta-llama/Llama-4-Scout-17B-16E-Instruct"
+"Qwen/QwQ-32B"
+```
+
+2. Find a template of specific vllm or SGLang version
 
 ```python
 # export GMI_CLOUD_CLIENT_ID=<YOUR_CLIENT_ID>
@@ -146,55 +161,67 @@ picked_template_name = "gmi_sglang_0.4.5.post1"
 serve_command = "python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --trust-remote-code --mem-fraction-static 0.8 --tp 2"
 ```
 
-4. Create an artifact and upload custom model. The artifact can be reused to create inference tasks later. Artifact also suggests recommended resources for each inference server replica
+4. Create an artifact. you can pass `pre_download_model` parameter. If you want custom model, upload model checkpoint to the artifactThe artifact can be reused to create inference tasks later. Artifact also suggests recommended resources for each inference server replica
 
 ```python
-artifact_id, recommended_replica_resources = cli.artifact_manager.create_artifact_from_template_name(
-    artifact_template_name=picked_template_name,
-    env_parameters={
-        "SERVER_COMMAND": serve_command,
-        "GPU_TYPE": "H100",
-    }
+artifact_name = "artifact_hello_world"
+artifact_id, recommended_replica_resources = cli.artifact_manager.create_artifact_for_serve_command_and_custom_model(
+    template_name=picked_template_name,
+    artifact_name=artifact_name,
+    serve_command=serve_command,
+    gpu_type="H100",
+    artifact_description="This is a test artifact",
+    pre_download_model=pick_pre_downloaded_model,
 )
 print(f"Created artifact {artifact_id} with recommended resources: {recommended_replica_resources}")
+```
 
-# Upload model files to artifact
+Alternatively, Upload a custom model checkpoint to artifact
+```python
 cli.artifact_manager.upload_model_files_to_artifact(artifact_id, model_checkpoint_save_dir)
+
+# Maybe Wait 10 minutes for the artifact to be ready
+time.sleep(10 * 60)
 ```
 
 5. Create Inference task (defining min/max inference replica), start and wait
 
 ```python
-new_task = Task(
-    config=TaskConfig(
-        ray_task_config=RayTaskConfig(
-            artifact_id=artifact_id,
-            file_path="serve",
-            deployment_name="app",
-            replica_resource=recommended_replica_resources,
-        ),
-        task_scheduling = TaskScheduling(
-            scheduling_oneoff=OneOffScheduling(
-                trigger_timestamp=int(datetime.now().timestamp()),
-                min_replicas=1,
-                max_replicas=4,
-            )
-        ),
-    ),
-)
-task = cli.task_manager.create_task(new_task)
-task_id = task.task_id
-task = cli.task_manager.get_task(task_id)
+# Create Task based on Artifact
+new_task_id = cli.task_manager.create_task_from_artifact_id(artifact_id, recommended_replica_resources, TaskScheduling(
+    scheduling_oneoff=OneOffScheduling(
+        trigger_timestamp=int(datetime.now().timestamp()),
+        min_replicas=1,
+        max_replicas=4,
+    )
+))
+task = cli.task_manager.get_task(new_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.task_manager.start_task_and_wait(task_id)
+cli.task_manager.start_task_and_wait(new_task_id)
 ```
 
-6. Test with sample chat completion request
+6. Test with sample chat completion request with OpenAI client
 
 ```python
-print(call_chat_completion(cli, task_id))
+pi_key = "<YOUR_API_KEY>"
+endpoint_url = cli.task_manager.get_task_endpoint_url(new_task_id)
+open_ai = OpenAI(
+    base_url=os.getenv("OPENAI_API_BASE", f"https://{endpoint_url}/serve/v1/"),
+    api_key=api_key
+)
+# Make a chat completion request using the new OpenAI client.
+completion = open_ai.chat.completions.create(
+    model=picked_template_name,
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Who are you?"},
+    ],
+    max_tokens=500,
+    temperature=0.7
+)
+print(completion.choices[0].message.content)
 ```
 
 

gmicloud-0.1.10/gmicloud/_internal/_client/_auth_config.py

@@ -0,0 +1,78 @@
+import os
+import jwt
+import time
+import json
+import logging
+import threading
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+CONFIG_FILE_NAME = ".gmicloud.config.json"
+
+# create the thread lock object56
+lock = threading.Lock()
+
+def _read_config_file()->dict|None:
+    """Read the config file."""
+    base_dir = Path.home()
+    config_file_path =os.path.join(base_dir,CONFIG_FILE_NAME)
+    if not os.path.exists(config_file_path):
+        return None
+    with lock:
+        # open the config file, read mode with lock
+        with open(config_file_path,"r") as fr:
+            return json.loads(fr.read())
+
+
+def _write_config_file(config_file_path:str,config_dic:dict)->None:
+    """Write the config file."""
+    with lock:
+        # open the config file, write mode with lock
+        with open(config_file_path,"w") as fw:
+            # transform the config dictionary to JSON format and write it to the file
+            fw.write(json.dumps(config_dic))
+
+
+def write_user_refresh_token_to_system_config(email:str,refresh_token:str)->bool:
+    """Write the user refresh token to the system config file."""
+    base_dir = Path.home()
+    config_file_path = os.path.join(base_dir,CONFIG_FILE_NAME)
+    try:
+        # check the config file is exists. if not, create it, if yes, update the refresh token
+        if not os.path.exists(config_file_path):
+            config_dic = { email : {"refresh_token": refresh_token} }
+            _write_config_file(config_file_path,config_dic)
+        else:
+            config_dic = _read_config_file()
+            if not config_dic.get(email):
+                config_dic[email] = dict()
+            config_dic[email] = {"refresh_token": refresh_token}
+            _write_config_file(config_file_path,config_dic)
+    except Exception as e:
+        logger.error("write file wrong :", e)
+        return False
+    return True
+
+
+def get_user_refresh_token_from_system_config(email:str)->str|None:
+    """Get the user refresh token from the system config file."""
+    config_dic = _read_config_file()
+    if not config_dic or not config_dic.get(email):
+        return None
+    return config_dic[email]["refresh_token"]
+
+
+def _parese_refresh_token(refresh_token:str)->dict:
+    """Parse the refresh token."""
+    return jwt.decode(refresh_token, options={"verify_signature": False})
+
+
+def is_refresh_token_expired(refresh_token:str)->bool:
+    """Check the refresh token is expired. if expired, return True, else return False."""
+    try:
+        refresh_token_time = _parese_refresh_token(refresh_token)['exp']
+    except Exception as e:
+        logger.error("parse refresh token wrong :", e)
+        return True
+    return refresh_token_time < time.time()

{gmicloud-0.1.7 → gmicloud-0.1.10}/gmicloud/_internal/_client/_http_client.py

@@ -57,28 +57,28 @@ class HTTPClient:
             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.")
+                raise UnauthorizedError(f"Unauthorized Error : {response.status_code} - Access token expired or invalid.")
             elif response.status_code != 200 and response.status_code != 201:
-                if url.find("ie/artifact") != -1 or url.find("ie/task") != -1:
+                if url.find("ie/artifact") != -1 or url.find("ie/task") != -1 or url.find("ie/requestqueue") != -1:
                     error_message = response.json().get('error', 'Unknown error')
                 else:
                     error_message = response.json().get('message', 'Unknown error')
-                raise APIError(f"HTTP Request failed: {error_message}")
+                raise APIError(f"HTTP Request failed: {response.status_code} - {error_message}")
             # Raise for HTTP errors
             response.raise_for_status()
 
         except requests.exceptions.RequestException as e:
-            raise APIError(f"HTTP Request failed: {str(e)}")
+            raise APIError(f"HTTP Request failed: {response.status_code} - {str(e)}")
         except ValueError as e:
             # Fallback if response JSON is invalid
-            raise APIError(f"Failed to parse JSON response: {response.text}")
+            raise APIError(f"Failed to parse JSON response: {response.status_code} - {response.text}")
 
         if response.headers.get(CONTENT_TYPE_HEADER).find(JSON_CONTENT_TYPE) != -1:
             return response.json()
         elif response.headers.get(CONTENT_TYPE_HEADER).find(TEXT_CONTENT_TYPE) != -1:
-            raise APIError(f"Got text response: {response.text}")
+            raise APIError(f"Got text response: {response.status_code} - {response.text}")
         else:
-            raise APIError(f"Unsupported content type: {response.headers.get(CONTENT_TYPE_HEADER)}")
+            raise APIError(f"Unsupported content type: {response.status_code} - {response.headers.get(CONTENT_TYPE_HEADER)}")
 
     def post(self, endpoint, custom_headers=None, data=None):
         """

{gmicloud-0.1.7 → gmicloud-0.1.10}/gmicloud/_internal/_client/_iam_client.py

@@ -6,7 +6,11 @@ from ._http_client import HTTPClient
 from .._config import IAM_SERVICE_BASE_URL
 from .._models import *
 from .._constants import CLIENT_ID_HEADER, AUTHORIZATION_HEADER
-
+from ._auth_config import (
+    get_user_refresh_token_from_system_config,
+    write_user_refresh_token_to_system_config,
+    is_refresh_token_expired
+)
 logger = logging.getLogger(__name__)
 
 
@@ -38,42 +42,50 @@ class IAMClient:
         Returns True if login is successful, otherwise False.
         """
         try:
-            custom_headers = {CLIENT_ID_HEADER: self._client_id}
-            req = AuthTokenRequest(email=self._email, password=self._password)
-            auth_tokens_result = self.client.post("/me/auth-tokens", custom_headers, req.model_dump())
-
-            if not auth_tokens_result:
-                logger.error("Login failed: Received empty response from auth-tokens endpoint")
-                return False
-
-            auth_tokens_resp = AuthTokenResponse.model_validate(auth_tokens_result)
-
-            # Handle 2FA
-            if auth_tokens_resp.is2FARequired:
-                for attempt in range(3):
-                    code = input(f"Attempt {attempt + 1}/3: Please enter the 2FA code: ")
-                    create_session_req = CreateSessionRequest(
-                        type="native", authToken=auth_tokens_resp.authToken, otpCode=code
-                    )
-                    try:
-                        session_result = self.client.post("/me/sessions", custom_headers,
-                                                          create_session_req.model_dump())
-                        if session_result:
-                            break
-                    except RequestException:
-                        logger.warning("Invalid 2FA code, please try again.")
-                        if attempt == 2:
-                            logger.error("Failed to create session after 3 incorrect 2FA attempts.")
-                            return False
+            # Check config refresh token is available and is not expired, if yes ,refresh it
+            temp_refresh_token = get_user_refresh_token_from_system_config(self._email)
+            if temp_refresh_token and not is_refresh_token_expired(temp_refresh_token):
+                self._refresh_token = temp_refresh_token
+                self.refresh_token()
             else:
-                create_session_req = CreateSessionRequest(type="native", authToken=auth_tokens_resp.authToken,
-                                                          otpCode=None)
-                session_result = self.client.post("/me/sessions", custom_headers, create_session_req.model_dump())
-
-            create_session_resp = CreateSessionResponse.model_validate(session_result)
-
-            self._access_token = create_session_resp.accessToken
-            self._refresh_token = create_session_resp.refreshToken
+                custom_headers = {CLIENT_ID_HEADER: self._client_id}
+                req = AuthTokenRequest(email=self._email, password=self._password)
+                auth_tokens_result = self.client.post("/me/auth-tokens", custom_headers, req.model_dump())
+
+                if not auth_tokens_result:
+                    logger.error("Login failed: Received empty response from auth-tokens endpoint")
+                    return False
+
+                auth_tokens_resp = AuthTokenResponse.model_validate(auth_tokens_result)
+
+                # Handle 2FA
+                if auth_tokens_resp.is2FARequired:
+                    for attempt in range(3):
+                        code = input(f"Attempt {attempt + 1}/3: Please enter the 2FA code: ")
+                        create_session_req = CreateSessionRequest(
+                            type="native", authToken=auth_tokens_resp.authToken, otpCode=code
+                        )
+                        try:
+                            session_result = self.client.post("/me/sessions", custom_headers,
+                                                            create_session_req.model_dump())
+                            if session_result:
+                                break
+                        except RequestException:
+                            logger.warning("Invalid 2FA code, please try again.")
+                            if attempt == 2:
+                                logger.error("Failed to create session after 3 incorrect 2FA attempts.")
+                                return False
+                else:
+                    create_session_req = CreateSessionRequest(type="native", authToken=auth_tokens_resp.authToken,
+                                                            otpCode=None)
+                    session_result = self.client.post("/me/sessions", custom_headers, create_session_req.model_dump())
+
+                create_session_resp = CreateSessionResponse.model_validate(session_result)
+
+                self._access_token = create_session_resp.accessToken
+                self._refresh_token = create_session_resp.refreshToken
+                # first login write refresh token to system config
+                write_user_refresh_token_to_system_config(self._email,self._refresh_token)
             self._user_id = self.parse_user_id()
 
             # Fetch profile to get organization ID
@@ -96,7 +108,12 @@ class IAMClient:
         """
         try:
             custom_headers = {CLIENT_ID_HEADER: self._client_id}
-            result = self.client.patch("/me/sessions", custom_headers, {"refreshToken": self._refresh_token})
+            try:
+                result = self.client.patch("/me/sessions", custom_headers, {"refreshToken": self._refresh_token})
+            except Exception as err:
+                logger.error(f"{str(err)}, please re-login.")
+                write_user_refresh_token_to_system_config(self._email,"")
+                return False
 
             if not result:
                 logger.error("Failed to refresh token: Empty response received")
@@ -105,7 +122,9 @@ class IAMClient:
             resp = CreateSessionResponse.model_validate(result)
             self._access_token = resp.accessToken
             self._refresh_token = resp.refreshToken
-
+            # the _refresh_token will be updated when call this function
+            # so write it to system config file for update the _refresh_token expired time
+            write_user_refresh_token_to_system_config(self._email,self._refresh_token)
             return True
         except (RequestException, ValueError) as e:
             logger.error(f"Token refresh failed: {e}")

gmicloud-0.1.10/gmicloud/_internal/_client/_video_client.py

@@ -0,0 +1,111 @@
+
+import logging
+from requests.exceptions import RequestException
+
+from ._http_client import HTTPClient
+from ._decorator import handle_refresh_token
+from ._iam_client import IAMClient
+from .._config import IAM_SERVICE_BASE_URL
+from .._models import *
+from .._exceptions import formated_exception
+
+logger = logging.getLogger(__name__)
+
+
+class VideoClient:
+    """
+    A client for interacting with the video service API.
+
+    This client provides methods to retrieve, create, update, and stop video tasks
+    through HTTP calls to the video service.
+    """
+
+    def __init__(self, iam_client: IAMClient):
+        """
+        Initializes the VideoClient with the given base URL for the video service.
+        """
+        self.client = HTTPClient(IAM_SERVICE_BASE_URL+ "/ie/requestqueue")
+        self.iam_client = iam_client
+
+
+    @handle_refresh_token
+    def get_request_detail(self, request_id: str) -> GetRequestResponse | dict:
+        """
+        Retrieves detailed information about a specific request by its ID. This endpoint requires authentication with a bearer token and only returns requests belonging to the authenticated organization.
+
+        :param request_id: The ID of the request to be retrieved.
+        :return: Details of the GetRequestResponse successfully retrieved
+        """
+        try:
+            response = self.client.get(f"/requests/{request_id}", self.iam_client.get_custom_headers())
+            return GetRequestResponse.model_validate(response) if response else None
+        except Exception as e:
+            logger.error(f"An unexpected error occurred while retrieving request details for {request_id}: {e}")
+            return formated_exception(e)
+
+
+    @handle_refresh_token
+    def get_requests(self, model_id: str) -> List[GetRequestResponse] | dict:
+        """
+        Retrieves a list of requests submitted by the authenticated user for a specific model. This endpoint requires authentication with a bearer token and filters results by the authenticated organization.
+
+        :param model_id: The ID of the model to be retrieved.
+        :return: List of GetRequestResponse successfully retrieved
+        """
+        try:
+            response = self.client.get("/requests", self.iam_client.get_custom_headers(), {"model_id": model_id})
+            requests = response.get('requests', []) if response else []
+            return [GetRequestResponse.model_validate(req) for req in requests] if requests else None
+        except Exception as e:
+            logger.error(f"An unexpected error occurred while retrieving requests for model {model_id}: {e}")
+            return formated_exception(e)
+
+
+    @handle_refresh_token
+    def create_request(self, request: SubmitRequestRequest) -> SubmitRequestResponse | dict:
+        """
+        Submits a new asynchronous request to process a specified model with provided parameters. This endpoint requires authentication with a bearer token.
+
+        :param request: The request data to be created by SubmitRequestRequest model.
+        :return: The created request data as SubmitRequestResponse model.
+        """
+        try:
+            response = self.client.post("/requests", self.iam_client.get_custom_headers(), request.model_dump())
+            return SubmitRequestResponse.model_validate(response) if response else None
+        except Exception as e:
+            logger.error(f"An unexpected error occurred while creating a request: {e}")
+            return formated_exception(e)
+
+
+    @handle_refresh_token
+    def get_model_detail(self, model_id: str) -> GetModelResponse | dict:
+        """
+        Retrieves detailed information about a specific model by its ID.
+
+        :param model_id: The ID of the model to be retrieved.
+        :return: Details of the GetModelResponse model successfully retrieved.
+        """
+        try:
+            response = self.client.get(f"/models/{model_id}", self.iam_client.get_custom_headers())
+            return GetModelResponse.model_validate(response) if response else None
+        except Exception as e:
+            logger.error(f"An unexpected error occurred while retrieving model details for {model_id}: {e}")
+            return formated_exception(e)
+    
+
+    @handle_refresh_token
+    def get_models(self) -> List[GetModelResponse] | dict:
+        """
+        Retrieves a list of available models from the video service.
+
+        :return: A list of GetModelResponse model successfully retrieved.
+        """
+        try:
+            response = self.client.get("/models", self.iam_client.get_custom_headers())
+            models = response.get('models', []) if response else []
+            return [GetModelResponse.model_validate(model) for model in models] if models else None
+        except Exception as e:
+            logger.error(f"An unexpected error occurred while retrieving models: {e}")
+            return formated_exception(e)
+
+

{gmicloud-0.1.7 → gmicloud-0.1.10}/gmicloud/_internal/_config.py

@@ -3,7 +3,8 @@
 # TASK_SERVICE_BASE_URL = "https://ce-tot.gmicloud-dev.com/api/v1/ie/task"
 # IAM_SERVICE_BASE_URL = "https://ce-tot.gmicloud-dev.com/api/v1"
 
+
 # Prod environment
-ARTIFACT_SERVICE_BASE_URL = "https://inference-engine.gmicloud.ai/api/v1/ie/artifact"
-TASK_SERVICE_BASE_URL = "https://inference-engine.gmicloud.ai/api/v1/ie/task"
-IAM_SERVICE_BASE_URL = "https://inference-engine.gmicloud.ai/api/v1"
+ARTIFACT_SERVICE_BASE_URL = "https://console.gmicloud.ai/api/v1/ie/artifact"
+TASK_SERVICE_BASE_URL = "https://console.gmicloud.ai/api/v1/ie/task"
+IAM_SERVICE_BASE_URL = "https://console.gmicloud.ai/api/v1"

{gmicloud-0.1.7 → gmicloud-0.1.10}/gmicloud/_internal/_enums.py

@@ -24,6 +24,7 @@ class TaskEndpointStatus(str, Enum):
     UNREADY = "unready"
     NEW = "new"
 
+
 class TaskStatus(str, Enum):
     IDLE = "idle"
     STARTING = "starting"
@@ -32,7 +33,24 @@ class TaskStatus(str, Enum):
     NEEDSTOP = "needstop"
     ARCHIVED = "archived"
 
+
 class ModelParameterType(str, Enum):
     NUMERIC = "numeric"
     TEXT = "text"
-    BOOLEAN = "boolean"
+    BOOLEAN = "boolean"
+
+
+class RequestStatus(Enum):
+    CREATED = "created"
+    QUEUED = "queued"
+    DISPATCHED = "dispatched"
+    PROCESSING = "processing"
+    SUCCESS = "success"
+    FAILED = "failed"
+    CANCELLED = "cancelled"
+
+
+class HostType(Enum):
+    DEFAULT = ""
+    INTERNAL = "internal"
+    EXTERNAL = "external"