orq-ai-sdk 4.3.0rc0__tar.gz → 4.3.0rc2__tar.gz

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orq-ai-sdk
-Version: 4.3.0rc0
+Version: 4.3.0rc2
 Summary: Python Client SDK for the Orq API.
 Author: Orq
 Project-URL: repository, https://github.com/orq-ai/orq-python.git

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "orq-ai-sdk"
-version = "4.3.0-rc.0"
+version = "4.3.0-rc.2"
 description = "Python Client SDK for the Orq API."
 authors = [{ name = "Orq" },]
 readme = "README-PYPI.md"

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/src/orq_ai_sdk/_version.py

@@ -3,10 +3,10 @@
 import importlib.metadata
 
 __title__: str = "orq-ai-sdk"
-__version__: str = "4.3.0-rc.0"
+__version__: str = "4.3.0-rc.2"
 __openapi_doc_version__: str = "2.0"
 __gen_version__: str = "2.799.0"
-__user_agent__: str = "speakeasy-sdk/python 4.3.0-rc.0 2.799.0 2.0 orq-ai-sdk"
+__user_agent__: str = "speakeasy-sdk/python 4.3.0-rc.2 2.799.0 2.0 orq-ai-sdk"
 
 try:
     if __package__ is not None:

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/src/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,
         )

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/src/orq_ai_sdk/edits.py

@@ -7,7 +7,7 @@ from orq_ai_sdk.models import createimageeditop as models_createimageeditop
 from orq_ai_sdk.types import OptionalNullable, UNSET
 from orq_ai_sdk.utils import get_security_from_env
 from orq_ai_sdk.utils.unmarshal_json_response import unmarshal_json_response
-from typing import Any, Mapping, Optional, Union
+from typing import Any, List, Mapping, Optional, Union
 
 
 class Edits(BaseSDK):
@@ -26,6 +26,37 @@ class Edits(BaseSDK):
             models_createimageeditop.CreateImageEditResponseFormat
         ] = None,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createimageeditop.CreateImageEditFallbacks],
+                List[models_createimageeditop.CreateImageEditFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditRetry,
+                models_createimageeditop.CreateImageEditRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditCache,
+                models_createimageeditop.CreateImageEditCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditLoadBalancer,
+                models_createimageeditop.CreateImageEditLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditTimeout,
+                models_createimageeditop.CreateImageEditTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createimageeditop.CreateImageEditOrq,
@@ -49,6 +80,12 @@ class Edits(BaseSDK):
         :param quality: The quality of the image that will be generated. Auto will automatically select the best quality for the given model.
         :param response_format: The format in which the generated images are returned. Some of the models only return the image in base64 format.
         :param user: A unique identifier representing your end-user, which can help 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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -77,6 +114,22 @@ class Edits(BaseSDK):
             quality=quality,
             response_format=response_format,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateImageEditFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateImageEditRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateImageEditCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateImageEditLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateImageEditTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateImageEditOrq]),
         )
 
@@ -149,6 +202,37 @@ class Edits(BaseSDK):
             models_createimageeditop.CreateImageEditResponseFormat
         ] = None,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createimageeditop.CreateImageEditFallbacks],
+                List[models_createimageeditop.CreateImageEditFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditRetry,
+                models_createimageeditop.CreateImageEditRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditCache,
+                models_createimageeditop.CreateImageEditCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditLoadBalancer,
+                models_createimageeditop.CreateImageEditLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditTimeout,
+                models_createimageeditop.CreateImageEditTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createimageeditop.CreateImageEditOrq,
@@ -172,6 +256,12 @@ class Edits(BaseSDK):
         :param quality: The quality of the image that will be generated. Auto will automatically select the best quality for the given model.
         :param response_format: The format in which the generated images are returned. Some of the models only return the image in base64 format.
         :param user: A unique identifier representing your end-user, which can help 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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -200,6 +290,22 @@ class Edits(BaseSDK):
             quality=quality,
             response_format=response_format,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateImageEditFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateImageEditRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateImageEditCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateImageEditLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateImageEditTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateImageEditOrq]),
         )
 

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/src/orq_ai_sdk/embeddings.py

@@ -7,7 +7,7 @@ from orq_ai_sdk.models import createembeddingop as models_createembeddingop
 from orq_ai_sdk.types import OptionalNullable, UNSET
 from orq_ai_sdk.utils import 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 Embeddings(BaseSDK):
@@ -22,6 +22,37 @@ class Embeddings(BaseSDK):
         encoding_format: Optional[models_createembeddingop.EncodingFormat] = "float",
         dimensions: Optional[float] = None,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createembeddingop.CreateEmbeddingFallbacks],
+                List[models_createembeddingop.CreateEmbeddingFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingRetry,
+                models_createembeddingop.CreateEmbeddingRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingCache,
+                models_createembeddingop.CreateEmbeddingCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingLoadBalancer,
+                models_createembeddingop.CreateEmbeddingLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingTimeout,
+                models_createembeddingop.CreateEmbeddingTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createembeddingop.CreateEmbeddingOrq,
@@ -42,6 +73,12 @@ class Embeddings(BaseSDK):
         :param encoding_format: Type of the document element
         :param dimensions: The number of dimensions the resulting output embeddings should have.
         :param user: A unique identifier representing your end-user
+        :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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -67,6 +104,22 @@ class Embeddings(BaseSDK):
             encoding_format=encoding_format,
             dimensions=dimensions,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateEmbeddingFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateEmbeddingRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateEmbeddingCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateEmbeddingLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateEmbeddingTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateEmbeddingOrq]),
         )
 
@@ -135,6 +188,37 @@ class Embeddings(BaseSDK):
         encoding_format: Optional[models_createembeddingop.EncodingFormat] = "float",
         dimensions: Optional[float] = None,
         user: Optional[str] = None,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createembeddingop.CreateEmbeddingFallbacks],
+                List[models_createembeddingop.CreateEmbeddingFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingRetry,
+                models_createembeddingop.CreateEmbeddingRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingCache,
+                models_createembeddingop.CreateEmbeddingCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingLoadBalancer,
+                models_createembeddingop.CreateEmbeddingLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingTimeout,
+                models_createembeddingop.CreateEmbeddingTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createembeddingop.CreateEmbeddingOrq,
@@ -155,6 +239,12 @@ class Embeddings(BaseSDK):
         :param encoding_format: Type of the document element
         :param dimensions: The number of dimensions the resulting output embeddings should have.
         :param user: A unique identifier representing your end-user
+        :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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -180,6 +270,22 @@ class Embeddings(BaseSDK):
             encoding_format=encoding_format,
             dimensions=dimensions,
             user=user,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateEmbeddingFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(
+                retry, Optional[models.CreateEmbeddingRetry]
+            ),
+            cache=utils.get_pydantic_model(
+                cache, Optional[models.CreateEmbeddingCache]
+            ),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateEmbeddingLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateEmbeddingTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateEmbeddingOrq]),
         )
 

{orq_ai_sdk-4.3.0rc0 → orq_ai_sdk-4.3.0rc2}/src/orq_ai_sdk/generations.py

@@ -7,7 +7,7 @@ from orq_ai_sdk.models import createimageop as models_createimageop
 from orq_ai_sdk.types import OptionalNullable, UNSET
 from orq_ai_sdk.utils import 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 Generations(BaseSDK):
@@ -27,6 +27,37 @@ class Generations(BaseSDK):
         ] = UNSET,
         size: OptionalNullable[str] = UNSET,
         style: OptionalNullable[models_createimageop.Style] = UNSET,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createimageop.CreateImageFallbacks],
+                List[models_createimageop.CreateImageFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createimageop.CreateImageRetry,
+                models_createimageop.CreateImageRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createimageop.CreateImageCache,
+                models_createimageop.CreateImageCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createimageop.CreateImageLoadBalancer,
+                models_createimageop.CreateImageLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createimageop.CreateImageTimeout,
+                models_createimageop.CreateImageTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createimageop.CreateImageOrq,
@@ -53,6 +84,12 @@ class Generations(BaseSDK):
         :param response_format: The format in which generated images are returned. Must be one of `url` or `b64_json`. This parameter isn't supported for `gpt-image-1` which will always return base64-encoded images.
         :param size: The size of the generated images. Must be one of the specified sizes for each model.
         :param style: The style of the generated images. This parameter is only supported for `openai/dall-e-3`. Must be one of `vivid` or `natural`.
+        :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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -84,6 +121,18 @@ class Generations(BaseSDK):
             response_format=response_format,
             size=size,
             style=style,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateImageFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(retry, Optional[models.CreateImageRetry]),
+            cache=utils.get_pydantic_model(cache, Optional[models.CreateImageCache]),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateImageLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateImageTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateImageOrq]),
         )
 
@@ -157,6 +206,37 @@ class Generations(BaseSDK):
         ] = UNSET,
         size: OptionalNullable[str] = UNSET,
         style: OptionalNullable[models_createimageop.Style] = UNSET,
+        name: Optional[str] = None,
+        fallbacks: Optional[
+            Union[
+                List[models_createimageop.CreateImageFallbacks],
+                List[models_createimageop.CreateImageFallbacksTypedDict],
+            ]
+        ] = None,
+        retry: Optional[
+            Union[
+                models_createimageop.CreateImageRetry,
+                models_createimageop.CreateImageRetryTypedDict,
+            ]
+        ] = None,
+        cache: Optional[
+            Union[
+                models_createimageop.CreateImageCache,
+                models_createimageop.CreateImageCacheTypedDict,
+            ]
+        ] = None,
+        load_balancer: Optional[
+            Union[
+                models_createimageop.CreateImageLoadBalancer,
+                models_createimageop.CreateImageLoadBalancerTypedDict,
+            ]
+        ] = None,
+        timeout: Optional[
+            Union[
+                models_createimageop.CreateImageTimeout,
+                models_createimageop.CreateImageTimeoutTypedDict,
+            ]
+        ] = None,
         orq: Optional[
             Union[
                 models_createimageop.CreateImageOrq,
@@ -183,6 +263,12 @@ class Generations(BaseSDK):
         :param response_format: The format in which generated images are returned. Must be one of `url` or `b64_json`. This parameter isn't supported for `gpt-image-1` which will always return base64-encoded images.
         :param size: The size of the generated images. Must be one of the specified sizes for each model.
         :param style: The style of the generated images. This parameter is only supported for `openai/dall-e-3`. Must be one of `vivid` or `natural`.
+        :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:
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
@@ -214,6 +300,18 @@ class Generations(BaseSDK):
             response_format=response_format,
             size=size,
             style=style,
+            name=name,
+            fallbacks=utils.get_pydantic_model(
+                fallbacks, Optional[List[models.CreateImageFallbacks]]
+            ),
+            retry=utils.get_pydantic_model(retry, Optional[models.CreateImageRetry]),
+            cache=utils.get_pydantic_model(cache, Optional[models.CreateImageCache]),
+            load_balancer=utils.get_pydantic_model(
+                load_balancer, Optional[models.CreateImageLoadBalancer]
+            ),
+            timeout=utils.get_pydantic_model(
+                timeout, Optional[models.CreateImageTimeout]
+            ),
             orq=utils.get_pydantic_model(orq, Optional[models.CreateImageOrq]),
         )