orq-ai-sdk 4.2.0rc28__py3-none-any.whl → 4.2.6__py3-none-any.whl

orq_ai_sdk/deployments.py

@@ -9,6 +9,7 @@ from orq_ai_sdk.models import (
     deploymentgetconfigop as models_deploymentgetconfigop,
     deploymentstreamop as models_deploymentstreamop,
     invokedeploymentrequest as models_invokedeploymentrequest,
+    publicidentity as models_publicidentity,
 )
 from orq_ai_sdk.types import OptionalNullable, UNSET
 from orq_ai_sdk.utils import eventstreaming, get_security_from_env
@@ -48,6 +49,12 @@ class Deployments(BaseSDK):
                 List[models_invokedeploymentrequest.MessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -90,6 +97,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -126,6 +134,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.Messages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,
@@ -222,6 +233,12 @@ class Deployments(BaseSDK):
                 List[models_invokedeploymentrequest.MessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -264,6 +281,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -300,6 +318,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.Messages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,
@@ -591,6 +612,12 @@ class Deployments(BaseSDK):
                 List[models_deploymentgetconfigop.DeploymentGetConfigMessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -634,6 +661,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -670,6 +698,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.DeploymentGetConfigMessages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,
@@ -765,6 +796,12 @@ class Deployments(BaseSDK):
                 List[models_deploymentgetconfigop.DeploymentGetConfigMessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -808,6 +845,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -844,6 +882,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.DeploymentGetConfigMessages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,
@@ -937,6 +978,12 @@ class Deployments(BaseSDK):
                 List[models_deploymentstreamop.DeploymentStreamMessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -978,6 +1025,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -1013,6 +1061,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.DeploymentStreamMessages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,
@@ -1115,6 +1166,12 @@ class Deployments(BaseSDK):
                 List[models_deploymentstreamop.DeploymentStreamMessagesTypedDict],
             ]
         ] = None,
+        identity: Optional[
+            Union[
+                models_publicidentity.PublicIdentity,
+                models_publicidentity.PublicIdentityTypedDict,
+            ]
+        ] = None,
         file_ids: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
         extra_params: Optional[Dict[str, Any]] = None,
@@ -1156,6 +1213,7 @@ class Deployments(BaseSDK):
         :param context: Key-value pairs that match your data model and fields declared in your deployment routing configuration
         :param prefix_messages: A list of messages to include after the `System` message, but before the  `User` and `Assistant` pairs configured in your deployment.
         :param messages: A list of messages to send to the deployment.
+        :param identity: Information about the identity making the request. If the identity does not exist, it will be created automatically.
         :param file_ids: A list of file IDs that are associated with the deployment request.
         :param metadata: Key-value pairs that you want to attach to the log generated by this request.
         :param extra_params: Utilized for passing additional parameters to the model provider. Exercise caution when using this feature, as the included parameters will overwrite any parameters specified in the deployment prompt configuration.
@@ -1191,6 +1249,9 @@ class Deployments(BaseSDK):
             messages=utils.get_pydantic_model(
                 messages, Optional[List[models.DeploymentStreamMessages]]
             ),
+            identity=utils.get_pydantic_model(
+                identity, Optional[models.PublicIdentity]
+            ),
             file_ids=file_ids,
             metadata=metadata,
             extra_params=extra_params,

orq_ai_sdk/edits.py

@@ -0,0 +1,258 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from .basesdk import BaseSDK
+from orq_ai_sdk import models, utils
+from orq_ai_sdk._hooks import HookContext
+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
+
+
+class Edits(BaseSDK):
+    def create(
+        self,
+        *,
+        model: str,
+        prompt: str,
+        image: Optional[Any] = None,
+        n: OptionalNullable[int] = 1,
+        size: OptionalNullable[str] = UNSET,
+        quality: OptionalNullable[
+            models_createimageeditop.CreateImageEditQuality
+        ] = UNSET,
+        response_format: Optional[
+            models_createimageeditop.CreateImageEditResponseFormat
+        ] = None,
+        user: Optional[str] = None,
+        orq: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditOrq,
+                models_createimageeditop.CreateImageEditOrqTypedDict,
+            ]
+        ] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateImageEditResponseBody:
+        r"""Create image edit
+
+        Edit an Image
+
+        :param model: The model to use for image edit. [Check models](https://docs.orq.ai/docs/ai-gateway-supported-models#image-models)
+        :param prompt: A text description of the desired image(s).
+        :param image: The image(s) to edit. Must be a supported image file or an array of images.  Each image should be a png, webp, or jpg file less than 50MB. You can provide up to 16 images.
+        :param n: The number of images to generate. Must be between 1 and 10.
+        :param size: The size of the generated images
+        :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 orq:
+        :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.CreateImageEditRequestBody(
+            model=model,
+            image=image,
+            prompt=prompt,
+            n=n,
+            size=size,
+            quality=quality,
+            response_format=response_format,
+            user=user,
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateImageEditOrq]),
+        )
+
+        req = self._build_request(
+            method="POST",
+            path="/v2/router/images/edits",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            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,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "multipart", models.CreateImageEditRequestBody
+            ),
+            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="createImageEdit",
+                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.CreateImageEditResponseBody, 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 create_async(
+        self,
+        *,
+        model: str,
+        prompt: str,
+        image: Optional[Any] = None,
+        n: OptionalNullable[int] = 1,
+        size: OptionalNullable[str] = UNSET,
+        quality: OptionalNullable[
+            models_createimageeditop.CreateImageEditQuality
+        ] = UNSET,
+        response_format: Optional[
+            models_createimageeditop.CreateImageEditResponseFormat
+        ] = None,
+        user: Optional[str] = None,
+        orq: Optional[
+            Union[
+                models_createimageeditop.CreateImageEditOrq,
+                models_createimageeditop.CreateImageEditOrqTypedDict,
+            ]
+        ] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateImageEditResponseBody:
+        r"""Create image edit
+
+        Edit an Image
+
+        :param model: The model to use for image edit. [Check models](https://docs.orq.ai/docs/ai-gateway-supported-models#image-models)
+        :param prompt: A text description of the desired image(s).
+        :param image: The image(s) to edit. Must be a supported image file or an array of images.  Each image should be a png, webp, or jpg file less than 50MB. You can provide up to 16 images.
+        :param n: The number of images to generate. Must be between 1 and 10.
+        :param size: The size of the generated images
+        :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 orq:
+        :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.CreateImageEditRequestBody(
+            model=model,
+            image=image,
+            prompt=prompt,
+            n=n,
+            size=size,
+            quality=quality,
+            response_format=response_format,
+            user=user,
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateImageEditOrq]),
+        )
+
+        req = self._build_request_async(
+            method="POST",
+            path="/v2/router/images/edits",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            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,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "multipart", models.CreateImageEditRequestBody
+            ),
+            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="createImageEdit",
+                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.CreateImageEditResponseBody, 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)

orq_ai_sdk/embeddings.py

@@ -0,0 +1,238 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from .basesdk import BaseSDK
+from orq_ai_sdk import models, utils
+from orq_ai_sdk._hooks import HookContext
+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
+
+
+class Embeddings(BaseSDK):
+    def create(
+        self,
+        *,
+        input_: Union[
+            models_createembeddingop.CreateEmbeddingInput,
+            models_createembeddingop.CreateEmbeddingInputTypedDict,
+        ],
+        model: str,
+        encoding_format: Optional[models_createembeddingop.EncodingFormat] = "float",
+        dimensions: Optional[float] = None,
+        user: Optional[str] = None,
+        orq: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingOrq,
+                models_createembeddingop.CreateEmbeddingOrqTypedDict,
+            ]
+        ] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateEmbeddingResponseBody:
+        r"""Create embeddings
+
+        Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
+
+        :param input: Input text to embed, encoded as a string or array of tokens.
+        :param model: ID of the model to use
+        :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 orq:
+        :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.CreateEmbeddingRequestBody(
+            input=input_,
+            model=model,
+            encoding_format=encoding_format,
+            dimensions=dimensions,
+            user=user,
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateEmbeddingOrq]),
+        )
+
+        req = self._build_request(
+            method="POST",
+            path="/v2/router/embeddings",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            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,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "json", models.CreateEmbeddingRequestBody
+            ),
+            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="createEmbedding",
+                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.CreateEmbeddingResponseBody, 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 create_async(
+        self,
+        *,
+        input_: Union[
+            models_createembeddingop.CreateEmbeddingInput,
+            models_createembeddingop.CreateEmbeddingInputTypedDict,
+        ],
+        model: str,
+        encoding_format: Optional[models_createembeddingop.EncodingFormat] = "float",
+        dimensions: Optional[float] = None,
+        user: Optional[str] = None,
+        orq: Optional[
+            Union[
+                models_createembeddingop.CreateEmbeddingOrq,
+                models_createembeddingop.CreateEmbeddingOrqTypedDict,
+            ]
+        ] = None,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
+    ) -> models.CreateEmbeddingResponseBody:
+        r"""Create embeddings
+
+        Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
+
+        :param input: Input text to embed, encoded as a string or array of tokens.
+        :param model: ID of the model to use
+        :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 orq:
+        :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.CreateEmbeddingRequestBody(
+            input=input_,
+            model=model,
+            encoding_format=encoding_format,
+            dimensions=dimensions,
+            user=user,
+            orq=utils.get_pydantic_model(orq, Optional[models.CreateEmbeddingOrq]),
+        )
+
+        req = self._build_request_async(
+            method="POST",
+            path="/v2/router/embeddings",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            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,
+            get_serialized_body=lambda: utils.serialize_request_body(
+                request, False, False, "json", models.CreateEmbeddingRequestBody
+            ),
+            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="createEmbedding",
+                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.CreateEmbeddingResponseBody, 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)