orq-ai-sdk 4.2.6__py3-none-any.whl → 4.3.0rc7__py3-none-any.whl

orq_ai_sdk/_hooks/globalhook.py

@@ -42,3 +42,4 @@ class GlobalHook(BeforeRequestHook):
             return httpx.Request(method=request.method, url=request.url, extensions=request.extensions, headers=request.headers, content=data)
 
         return request
+

orq_ai_sdk/_version.py

@@ -3,10 +3,10 @@
 import importlib.metadata
 
 __title__: str = "orq-ai-sdk"
-__version__: str = "4.2.6"
+__version__: str = "4.3.0-rc.7"
 __openapi_doc_version__: str = "2.0"
-__gen_version__: str = "2.799.0"
-__user_agent__: str = "speakeasy-sdk/python 4.2.6 2.799.0 2.0 orq-ai-sdk"
+__gen_version__: str = "2.801.2"
+__user_agent__: str = "speakeasy-sdk/python 4.3.0-rc.7 2.801.2 2.0 orq-ai-sdk"
 
 try:
     if __package__ is not None:

orq_ai_sdk/agents.py

@@ -363,6 +363,192 @@ class Agents(BaseSDK):
 
         raise models.APIError("Unexpected response received", http_res)
 
+    def list(
+        self,
+        *,
+        limit: Optional[float] = None,
+        starting_after: Optional[str] = None,
+        ending_before: Optional[str] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.ListAgentsResponseBody:
+        r"""List agents
+
+        Retrieves a comprehensive list of agents configured in your workspace. Supports pagination for large datasets and returns agents sorted by creation date (newest first). Each agent in the response includes its complete configuration: model settings with fallback options, instructions, tools, knowledge bases, memory stores, and execution parameters. Use pagination parameters to efficiently navigate through large collections of agents.
+
+        :param limit: A limit on the number of objects to be returned. Limit can range between 1 and 200. When not provided, returns all agents without pagination.
+        :param starting_after: A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
+        :param ending_before: A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+
+        if timeout_ms is None:
+            timeout_ms = 600000
+
+        if server_url is not None:
+            base_url = server_url
+        else:
+            base_url = self._get_url(base_url, url_variables)
+
+        request = models.ListAgentsRequest(
+            limit=limit,
+            starting_after=starting_after,
+            ending_before=ending_before,
+        )
+
+        req = self._build_request(
+            method="GET",
+            path="/v2/agents",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=False,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="application/json",
+            http_headers=http_headers,
+            security=self.sdk_configuration.security,
+            allow_empty_value=None,
+            timeout_ms=timeout_ms,
+        )
+
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, ["429", "500", "502", "503", "504"])
+
+        http_res = self.do_request(
+            hook_ctx=HookContext(
+                config=self.sdk_configuration,
+                base_url=base_url or "",
+                operation_id="ListAgents",
+                oauth2_scopes=None,
+                security_source=get_security_from_env(
+                    self.sdk_configuration.security, models.Security
+                ),
+            ),
+            request=req,
+            error_status_codes=["4XX", "5XX"],
+            retry_config=retry_config,
+        )
+
+        if utils.match_response(http_res, "200", "application/json"):
+            return unmarshal_json_response(models.ListAgentsResponseBody, http_res)
+        if utils.match_response(http_res, "4XX", "*"):
+            http_res_text = utils.stream_to_text(http_res)
+            raise models.APIError("API error occurred", http_res, http_res_text)
+        if utils.match_response(http_res, "5XX", "*"):
+            http_res_text = utils.stream_to_text(http_res)
+            raise models.APIError("API error occurred", http_res, http_res_text)
+
+        raise models.APIError("Unexpected response received", http_res)
+
+    async def list_async(
+        self,
+        *,
+        limit: Optional[float] = None,
+        starting_after: Optional[str] = None,
+        ending_before: Optional[str] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.ListAgentsResponseBody:
+        r"""List agents
+
+        Retrieves a comprehensive list of agents configured in your workspace. Supports pagination for large datasets and returns agents sorted by creation date (newest first). Each agent in the response includes its complete configuration: model settings with fallback options, instructions, tools, knowledge bases, memory stores, and execution parameters. Use pagination parameters to efficiently navigate through large collections of agents.
+
+        :param limit: A limit on the number of objects to be returned. Limit can range between 1 and 200. When not provided, returns all agents without pagination.
+        :param starting_after: A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
+        :param ending_before: A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+
+        if timeout_ms is None:
+            timeout_ms = 600000
+
+        if server_url is not None:
+            base_url = server_url
+        else:
+            base_url = self._get_url(base_url, url_variables)
+
+        request = models.ListAgentsRequest(
+            limit=limit,
+            starting_after=starting_after,
+            ending_before=ending_before,
+        )
+
+        req = self._build_request_async(
+            method="GET",
+            path="/v2/agents",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=False,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="application/json",
+            http_headers=http_headers,
+            security=self.sdk_configuration.security,
+            allow_empty_value=None,
+            timeout_ms=timeout_ms,
+        )
+
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, ["429", "500", "502", "503", "504"])
+
+        http_res = await self.do_request_async(
+            hook_ctx=HookContext(
+                config=self.sdk_configuration,
+                base_url=base_url or "",
+                operation_id="ListAgents",
+                oauth2_scopes=None,
+                security_source=get_security_from_env(
+                    self.sdk_configuration.security, models.Security
+                ),
+            ),
+            request=req,
+            error_status_codes=["4XX", "5XX"],
+            retry_config=retry_config,
+        )
+
+        if utils.match_response(http_res, "200", "application/json"):
+            return unmarshal_json_response(models.ListAgentsResponseBody, http_res)
+        if utils.match_response(http_res, "4XX", "*"):
+            http_res_text = await utils.stream_to_text_async(http_res)
+            raise models.APIError("API error occurred", http_res, http_res_text)
+        if utils.match_response(http_res, "5XX", "*"):
+            http_res_text = await utils.stream_to_text_async(http_res)
+            raise models.APIError("API error occurred", http_res, http_res_text)
+
+        raise models.APIError("Unexpected response received", http_res)
+
     def delete(
         self,
         *,
@@ -1425,192 +1611,6 @@ class Agents(BaseSDK):
 
         raise models.APIError("Unexpected response received", http_res)
 
-    def list(
-        self,
-        *,
-        limit: Optional[float] = None,
-        starting_after: Optional[str] = None,
-        ending_before: Optional[str] = None,
-        retries: OptionalNullable[utils.RetryConfig] = UNSET,
-        server_url: Optional[str] = None,
-        timeout_ms: Optional[int] = None,
-        http_headers: Optional[Mapping[str, str]] = None,
-    ) -> models.ListAgentsResponseBody:
-        r"""List agents
-
-        Retrieves a comprehensive list of agents configured in your workspace. Supports pagination for large datasets and returns agents sorted by creation date (newest first). Each agent in the response includes its complete configuration: model settings with fallback options, instructions, tools, knowledge bases, memory stores, and execution parameters. Use pagination parameters to efficiently navigate through large collections of agents.
-
-        :param limit: A limit on the number of objects to be returned. Limit can range between 1 and 200. When not provided, returns all agents without pagination.
-        :param starting_after: A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
-        :param ending_before: A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
-        :param retries: Override the default retry configuration for this method
-        :param server_url: Override the default server URL for this method
-        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
-        :param http_headers: Additional headers to set or replace on requests.
-        """
-        base_url = None
-        url_variables = None
-        if timeout_ms is None:
-            timeout_ms = self.sdk_configuration.timeout_ms
-
-        if timeout_ms is None:
-            timeout_ms = 600000
-
-        if server_url is not None:
-            base_url = server_url
-        else:
-            base_url = self._get_url(base_url, url_variables)
-
-        request = models.ListAgentsRequest(
-            limit=limit,
-            starting_after=starting_after,
-            ending_before=ending_before,
-        )
-
-        req = self._build_request(
-            method="GET",
-            path="/v2/agents/",
-            base_url=base_url,
-            url_variables=url_variables,
-            request=request,
-            request_body_required=False,
-            request_has_path_params=False,
-            request_has_query_params=True,
-            user_agent_header="user-agent",
-            accept_header_value="application/json",
-            http_headers=http_headers,
-            security=self.sdk_configuration.security,
-            allow_empty_value=None,
-            timeout_ms=timeout_ms,
-        )
-
-        if retries == UNSET:
-            if self.sdk_configuration.retry_config is not UNSET:
-                retries = self.sdk_configuration.retry_config
-
-        retry_config = None
-        if isinstance(retries, utils.RetryConfig):
-            retry_config = (retries, ["429", "500", "502", "503", "504"])
-
-        http_res = self.do_request(
-            hook_ctx=HookContext(
-                config=self.sdk_configuration,
-                base_url=base_url or "",
-                operation_id="ListAgents",
-                oauth2_scopes=None,
-                security_source=get_security_from_env(
-                    self.sdk_configuration.security, models.Security
-                ),
-            ),
-            request=req,
-            error_status_codes=["4XX", "5XX"],
-            retry_config=retry_config,
-        )
-
-        if utils.match_response(http_res, "200", "application/json"):
-            return unmarshal_json_response(models.ListAgentsResponseBody, http_res)
-        if utils.match_response(http_res, "4XX", "*"):
-            http_res_text = utils.stream_to_text(http_res)
-            raise models.APIError("API error occurred", http_res, http_res_text)
-        if utils.match_response(http_res, "5XX", "*"):
-            http_res_text = utils.stream_to_text(http_res)
-            raise models.APIError("API error occurred", http_res, http_res_text)
-
-        raise models.APIError("Unexpected response received", http_res)
-
-    async def list_async(
-        self,
-        *,
-        limit: Optional[float] = None,
-        starting_after: Optional[str] = None,
-        ending_before: Optional[str] = None,
-        retries: OptionalNullable[utils.RetryConfig] = UNSET,
-        server_url: Optional[str] = None,
-        timeout_ms: Optional[int] = None,
-        http_headers: Optional[Mapping[str, str]] = None,
-    ) -> models.ListAgentsResponseBody:
-        r"""List agents
-
-        Retrieves a comprehensive list of agents configured in your workspace. Supports pagination for large datasets and returns agents sorted by creation date (newest first). Each agent in the response includes its complete configuration: model settings with fallback options, instructions, tools, knowledge bases, memory stores, and execution parameters. Use pagination parameters to efficiently navigate through large collections of agents.
-
-        :param limit: A limit on the number of objects to be returned. Limit can range between 1 and 200. When not provided, returns all agents without pagination.
-        :param starting_after: A cursor for use in pagination. `starting_after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, ending with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `after=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the next page of the list.
-        :param ending_before: A cursor for use in pagination. `ending_before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 20 objects, starting with `01JJ1HDHN79XAS7A01WB3HYSDB`, your subsequent call can include `before=01JJ1HDHN79XAS7A01WB3HYSDB` in order to fetch the previous page of the list.
-        :param retries: Override the default retry configuration for this method
-        :param server_url: Override the default server URL for this method
-        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
-        :param http_headers: Additional headers to set or replace on requests.
-        """
-        base_url = None
-        url_variables = None
-        if timeout_ms is None:
-            timeout_ms = self.sdk_configuration.timeout_ms
-
-        if timeout_ms is None:
-            timeout_ms = 600000
-
-        if server_url is not None:
-            base_url = server_url
-        else:
-            base_url = self._get_url(base_url, url_variables)
-
-        request = models.ListAgentsRequest(
-            limit=limit,
-            starting_after=starting_after,
-            ending_before=ending_before,
-        )
-
-        req = self._build_request_async(
-            method="GET",
-            path="/v2/agents/",
-            base_url=base_url,
-            url_variables=url_variables,
-            request=request,
-            request_body_required=False,
-            request_has_path_params=False,
-            request_has_query_params=True,
-            user_agent_header="user-agent",
-            accept_header_value="application/json",
-            http_headers=http_headers,
-            security=self.sdk_configuration.security,
-            allow_empty_value=None,
-            timeout_ms=timeout_ms,
-        )
-
-        if retries == UNSET:
-            if self.sdk_configuration.retry_config is not UNSET:
-                retries = self.sdk_configuration.retry_config
-
-        retry_config = None
-        if isinstance(retries, utils.RetryConfig):
-            retry_config = (retries, ["429", "500", "502", "503", "504"])
-
-        http_res = await self.do_request_async(
-            hook_ctx=HookContext(
-                config=self.sdk_configuration,
-                base_url=base_url or "",
-                operation_id="ListAgents",
-                oauth2_scopes=None,
-                security_source=get_security_from_env(
-                    self.sdk_configuration.security, models.Security
-                ),
-            ),
-            request=req,
-            error_status_codes=["4XX", "5XX"],
-            retry_config=retry_config,
-        )
-
-        if utils.match_response(http_res, "200", "application/json"):
-            return unmarshal_json_response(models.ListAgentsResponseBody, http_res)
-        if utils.match_response(http_res, "4XX", "*"):
-            http_res_text = await utils.stream_to_text_async(http_res)
-            raise models.APIError("API error occurred", http_res, http_res_text)
-        if utils.match_response(http_res, "5XX", "*"):
-            http_res_text = await utils.stream_to_text_async(http_res)
-            raise models.APIError("API error occurred", http_res, http_res_text)
-
-        raise models.APIError("Unexpected response received", http_res)
-
     @deprecated(
         "warning: ** DEPRECATED ** - This will be removed in a future release, please migrate away from it as soon as possible."
     )

orq_ai_sdk/completions.py

@@ -8,7 +8,7 @@ from orq_ai_sdk.models import createcompletionop as models_createcompletionop
 from orq_ai_sdk.types import OptionalNullable, UNSET
 from orq_ai_sdk.utils import eventstreaming, get_security_from_env
 from orq_ai_sdk.utils.unmarshal_json_response import unmarshal_json_response
-from typing import Mapping, Optional, Union
+from typing import List, Mapping, Optional, Union
 
 
 class CreateAcceptEnum(str, Enum):
@@ -37,6 +37,37 @@ class Completions(BaseSDK):
         top_p: OptionalNullable[float] = 1,
         n: OptionalNullable[float] = 1,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createcompletionop.CreateCompletionFallbacks],
+                List[models_createcompletionop.CreateCompletionFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionRetry,
+                models_createcompletionop.CreateCompletionRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionCache,
+                models_createcompletionop.CreateCompletionCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionLoadBalancer,
+                models_createcompletionop.CreateCompletionLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionTimeout,
+                models_createcompletionop.CreateCompletionTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createcompletionop.CreateCompletionOrq,
@@ -66,6 +97,12 @@ class Completions(BaseSDK):
         :param top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
         :param n: How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota.
         :param user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
+        :param name: The name to display on the trace. If not specified, the default system name will be used.
+        :param fallbacks: Array of fallback models to use if primary model fails
+        :param retry: Retry configuration for the request
+        :param cache: Cache configuration for the request.
+        :param load_balancer: Load balancer configuration for the request.
+        :param timeout: Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured.
         :param orq: Leverage Orq's intelligent routing capabilities to enhance your AI application with enterprise-grade reliability and observability. Orq provides automatic request management including retries on failures, model fallbacks for high availability, identity-level analytics tracking, conversation threading, and dynamic prompt templating with variable substitution.
         :param stream:
         :param retries: Override the default retry configuration for this method
@@ -100,6 +137,22 @@ class Completions(BaseSDK):
             top_p=top_p,
             n=n,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateCompletionFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateCompletionRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateCompletionCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateCompletionLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateCompletionTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateCompletionOrq]),
             stream=stream,
         )
@@ -194,6 +247,37 @@ class Completions(BaseSDK):
         top_p: OptionalNullable[float] = 1,
         n: OptionalNullable[float] = 1,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createcompletionop.CreateCompletionFallbacks],
+                List[models_createcompletionop.CreateCompletionFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionRetry,
+                models_createcompletionop.CreateCompletionRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionCache,
+                models_createcompletionop.CreateCompletionCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionLoadBalancer,
+                models_createcompletionop.CreateCompletionLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createcompletionop.CreateCompletionTimeout,
+                models_createcompletionop.CreateCompletionTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createcompletionop.CreateCompletionOrq,
@@ -223,6 +307,12 @@ class Completions(BaseSDK):
         :param top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
         :param n: How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota.
         :param user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
+        :param name: The name to display on the trace. If not specified, the default system name will be used.
+        :param fallbacks: Array of fallback models to use if primary model fails
+        :param retry: Retry configuration for the request
+        :param cache: Cache configuration for the request.
+        :param load_balancer: Load balancer configuration for the request.
+        :param timeout: Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured.
         :param orq: Leverage Orq's intelligent routing capabilities to enhance your AI application with enterprise-grade reliability and observability. Orq provides automatic request management including retries on failures, model fallbacks for high availability, identity-level analytics tracking, conversation threading, and dynamic prompt templating with variable substitution.
         :param stream:
         :param retries: Override the default retry configuration for this method
@@ -257,6 +347,22 @@ class Completions(BaseSDK):
             top_p=top_p,
             n=n,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateCompletionFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateCompletionRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateCompletionCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateCompletionLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateCompletionTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateCompletionOrq]),
             stream=stream,
         )