All Classes and Interfaces
Class
Description
The multipart/form-data request body of a data part addition request for an upload.
Describes the parameters for audio output.
Object containing audio response data and its metadata.
Defines the possible descriptors for available audio operation responses.
Result information for an operation that transcribed spoken audio into written text.
Defines available options for the underlying response format of output transcription information.
The configuration information for an audio transcription request.
Extended information about a single segment of transcribed audio data.
Defines the timestamp granularities that can be requested on a verbose transcription response.
Extended information about a single transcribed word, as provided on responses when the 'word' timestamp granularity
is provided.
Result information for an operation that translated spoken audio into written text.
Defines available options for the underlying response format of output translation information.
The configuration information for an audio translation request.
Extended information about a single segment of translated audio data.
A representation of the available Azure OpenAI enhancement configurations.
Represents the output results of Azure enhancements to chat completions, as configured via the matching input
provided
in the request.
A representation of configuration data for a single Azure OpenAI chat extension.
A single instance of additional context information available when Azure OpenAI chat extensions are involved
in the generation of a corresponding chat completions response.
The retrieved document.
The reason for filtering the retrieved document.
A representation of the additional context information available when Azure OpenAI chat extensions are involved
in the generation of a corresponding chat completions response.
A representation of configuration data for a single Azure OpenAI chat extension.
A representation of the available options for the Azure OpenAI grounding enhancement.
A representation of the available options for the Azure OpenAI optical character recognition (OCR) enhancement.
A specific representation of configurable options for Azure Cosmos DB when using it as an Azure OpenAI chat
extension.
Parameters to use when configuring Azure OpenAI On Your Data chat extensions when using Azure Cosmos DB for
MongoDB vCore.
Optional settings to control how fields are processed when using a configured Azure Cosmos DB resource.
The grounding enhancement that returns the bounding box of the objects detected in the image.
A representation of a single polygon point as used by the Azure grounding enhancement.
A content line object consisting of an adjacent sequence of content elements, such as words and selection marks.
A span object that represents a detected object and its bounding box information.
Service version of AzureResponsesClient.
A specific representation of configurable options for Azure Search when using it as an Azure OpenAI chat
extension.
Parameters for Azure Cognitive Search when used as an Azure OpenAI chat extension.
Optional settings to control how fields are processed when using a configured Azure Search resource.
The type of Azure Search retrieval query that should be executed when using it as an Azure OpenAI chat extension.
The Batch object.
Defines the request to create a batch.
A Datum containing information about a Batch Error.
A list of Batch errors.
The BatchRequestCounts model.
The status of a batch.
The representation of a single prompt completion as part of an overall chat completions request.
Log probability information for a choice, as requested via 'logprobs' and 'top_logprobs'.
Values to specified the required modality for the model to use.
Representation of the response data from a chat completions request.
A tool call to a function tool, issued by the model in evaluation of a configured function tool, that represents
a function invocation needed for a subsequent chat completions request to resolve.
The definition information for a chat completions function tool that can call a function in response to a tool call.
The ChatCompletionsFunctionToolDefinitionFunction model.
A tool selection of a specific, named function tool that will limit chat completions to using the named function.
A response format for Chat Completions that restricts responses to emitting valid JSON objects.
A response format for Chat Completions that restricts responses to emitting JSON that conforms to a provided JSON
Schema for Structured Outputs.
The ChatCompletionsJsonSchemaResponseFormatJsonSchema model.
A tool selection of a specific, named function tool that will limit chat completions to using the named function.
An abstract representation of an explicit, named tool selection to use for a chat completions request.
The configuration information for a chat completions request.
An abstract representation of a response format configuration usable by Chat Completions.
The standard Chat Completions response format that can freely generate text and is not guaranteed to produce response
content that adheres to a specific schema.
An abstract representation of a tool call that must be resolved in a subsequent request to perform the requested
chat completion.
An abstract representation of a tool that can be used by the model to improve a chat completions response.
Represents the tool selection for chat completions.
Represents a generic policy for how a chat completions tool may be selected.
Options for streaming response.
An abstract representation of structured information about why a chat completions response terminated.
A structured chat content item containing audio data.
An abstract representation of a structured content item within a chat message.
A structured chat content item containing an image reference.
A representation of the possible image detail levels for image-based chat completions message content.
An internet location from which the model may retrieve an image.
A structured chat content item containing model refusal information for a structured outputs request.
A structured chat content item containing plain text.
A request chat message representing response or action from the assistant.
Developer-provided instructions that the model should follow, regardless of messages sent by the user.
A request chat message representing requested output from a configured function.
An abstract representation of a chat message as provided in a request.
A request chat message containing system instructions that influence how the model will generate a chat completions
response.
A request chat message representing requested output from a configured tool.
A request chat message representing user input to the assistant.
A representation of a chat message as received in a response.
A description of the intended purpose of a message within a chat completions interaction.
A representation of the log probability information for a single message content token.
A representation of the log probability information for a single content token, including a list of most likely
tokens if 'top_logprobs' were requested.
The representation of a single prompt completion as part of an overall completions request.
The request body of an upload completion request.
Representation of the response data from a completions request.
Representation of the manner in which a completions response concluded.
Representation of a log probabilities model for a completions generation.
The configuration information for a completions request.
Representation of the token counts processed for a completions request.
The CompletionsUsageCompletionTokensDetails model.
The CompletionsUsagePromptTokensDetails model.
Represents the outcome of an evaluation against a custom blocklist as performed by content filtering.
Represents the outcome of a detection operation against protected resources as performed by content filtering.
Describes a span within generated completion text.
Describes a span within generated completion text.
Represents a structured collection of result details for content filtering.
Represents the outcome of a detection operation performed by content filtering.
Information about filtered content severity level and if it has been filtered or not.
Information about content filtering evaluated against input data to Azure OpenAI.
Information about content filtering evaluated against generated model output.
Content filtering results for a single prompt in the request.
Ratings for the intensity and risk level of harmful content.
Defines values for CreateResponseRequestAccept.
The CreateResponsesRequest model.
Defines values for CreateResponsesRequestIncludable.
Defines values for CreateResponsesRequestModel.
The request body of an upload creation operation.
Defines values for CreateUploadRequestPurpose.
The file details for the "data" field.
The DeleteResponseResponse model.
A specific representation of configurable options for Elasticsearch when using it as an Azure OpenAI chat
extension.
Parameters to use when configuring Elasticsearch® as an Azure OpenAI chat extension.
Optional settings to control how fields are processed when using a configured Elasticsearch® resource.
The type of Elasticsearch® retrieval query that should be executed when using it as an Azure OpenAI chat extension.
Representation of a single embeddings relatedness comparison.
Representation of the response data from an embeddings request.
The configuration information for an embeddings request.
Measurement of the amount of tokens used in this request and response.
A status response from a file deletion operation.
The file details for the "file" field.
The possible values denoting the intended usage of a file.
The state of the file.
The name and arguments of a function that should be called, as generated by the model.
The name and arguments of a function that should be called, as generated by the model.
The definition of a caller-specified function that chat completions may invoke in response to matching user input.
A structure that specifies the exact name of a specific, request-provided function to use when processing a chat
completions operation.
Describes the content filtering result for the image generation request.
A representation of a single generated image, provided as either base64-encoded data or as a URL from which the image
may be retrieved.
Represents the request data used to generate images.
Describes the content filtering results for the prompt of a image generation request.
An image generation configuration that specifies how the model should prioritize quality, cost, and speed.
The format in which the generated images are returned.
The result of a successful image generation operation.
An image generation configuration that specifies how the model should incorporate realism and other visual
characteristics.
The desired size of generated images.
A structured chat content item containing audio data.
Values to describe the format of the input audio data.
Defines values for ListInputItemsRequestOrder.
A structured representation of a stop reason that signifies a token limit was reached before the model could
naturally
complete.
A specific representation of configurable options for a MongoDB chat extension configuration.
Parameters for the MongoDB chat extension.
The MongoDBChatExtensionParametersFieldsMapping model.
The authentication options for Azure OpenAI On Your Data when using access token.
The authentication options for Azure OpenAI On Your Data when using an API key.
The authentication options for Azure OpenAI On Your Data.
The authentication types supported with Azure OpenAI On Your Data.
The authentication options for Azure OpenAI On Your Data when using a connection string.
The context property.
The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based
on an internal embeddings model deployment name in the same Azure OpenAI resource.
The authentication options for Azure OpenAI On Your Data when using an Elasticsearch encoded API key.
The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based
on a public Azure OpenAI endpoint call for embeddings.
Represents the integrated vectorizer defined within the search resource.
The authentication options for Azure OpenAI On Your Data when using an Elasticsearch key and key ID pair.
The details of a a vectorization source, used by Azure OpenAI On Your Data when applying vector search, that is based
on a search service model ID.
The authentication options for Azure OpenAI On Your Data when using a system-assigned managed identity.
The authentication options for Azure OpenAI On Your Data when using a user-assigned managed identity.
The authentication options for Azure OpenAI On Your Data when using a username and password.
An abstract representation of a vectorization source for Azure OpenAI On Your Data with vector search.
Represents the available sources Azure OpenAI On Your Data can use to configure vectorization of data for use with
vector search.
The authentication options for Azure OpenAI On Your Data vector search when using access token.
The authentication options for Azure OpenAI On Your Data when using an API key.
The authentication options for Azure OpenAI On Your Data vector search.
The authentication types supported with Azure OpenAI On Your Data vector search.
Initializes a new instance of the asynchronous OpenAIClient type.
Initializes a new instance of the synchronous OpenAIClient type.
A builder for creating a new instance of the OpenAIClient type.
Represents an assistant that can call the model and use tools.
Service version of OpenAIClient.
The output audio format.
The response data for a requested list of items.
A specific representation of configurable options for Pinecone when using it as an Azure OpenAI chat
extension.
Parameters for configuring Azure OpenAI Pinecone chat extensions.
Optional settings to control how fields are processed when using a configured Pinecone resource.
Static predicted output content, such as the content of a text file that is being regenerated.
The types of predicted content.
Values for the reasoning.
Defines values for ResponseOutputTextAnnotationType.
A message item with the `assistant` role.
Initializes a new instance of the asynchronous ResponsesClient type.
Initializes a new instance of the synchronous ResponsesClient type.
A builder for creating a new instance of the ResponsesClient type.
Defines values for ResponsesComputerCallActionType.
The ResponsesComputerCallClickAction model.
Defines values for ResponsesComputerCallClickButtonType.
The ResponsesComputerCallDoubleClickAction model.
The ResponsesComputerCallDragAction model.
The ResponsesComputerCallDragActionPath model.
A tool call to a computer use tool.
The ResponsesComputerCallItemAction model.
The ResponsesComputerCallItemSafetyCheck model.
Defines values for ResponsesComputerCallItemStatus.
The ResponsesComputerCallKeyPressAction model.
The ResponsesComputerCallMoveAction model.
The ResponsesComputerCallOutputItem model.
The ResponsesComputerCallOutputItemOutput model.
Defines values for ResponsesComputerCallOutputItemOutputType.
The ResponsesComputerCallOutputItemScreenshot model.
Defines values for ResponsesComputerCallOutputItemStatus.
The ResponsesComputerCallScreenshotAction model.
The ResponsesComputerCallScrollAction model.
The ResponsesComputerCallTypeAction model.
The ResponsesComputerCallWaitAction model.
The ResponsesComputerTool model.
Defines values for ResponsesComputerToolEnvironment.
The ResponsesContent model.
Defines values for ResponsesContentType.
A message item with the `developer` role.
The ResponsesError model.
The ResponsesFileSearchCallItem model.
The ResponsesFileSearchCallItemResult model.
Defines values for ResponsesFileSearchCallItemStatus.
The ResponsesFileSearchTool model.
The ResponsesFileSearchToolRankingOptions model.
Defines values for ResponsesFileSearchToolRankingOptionsRanker.
The ResponsesFunctionCallItem model.
Defines values for ResponsesFunctionCallItemStatus.
The ResponsesFunctionCallOutput model.
Defines values for ResponsesFunctionCallOutputStatus.
The ResponsesFunctionTool model.
The ResponsesInputContentFile model.
The ResponsesInputContentImage model.
Defines values for ResponsesInputContentImageDetail.
The ResponsesInputContentText model.
The ResponsesInputItemList model.
The ResponsesItem model.
The ResponsesItemReferenceItem model.
Defines values for ResponsesItemType.
A response message item, representing a role and content.
The collection of valid roles for responses message items.
Defines values for ResponsesMessageStatus.
The ResponsesOutputContentRefusal model.
The ResponsesOutputContentText model.
The ResponsesOutputTextAnnotation model.
The ResponsesOutputTextAnnotationFileCitation model.
The ResponsesOutputTextAnnotationFilePath model.
Defines values for ResponsesOutputTextAnnotationType.
The ResponsesOutputTextAnnotationUrlCitation model.
**o-series models only**
Configuration options for reasoning models.
Defines values for ResponsesReasoningConfigurationEffort.
Defines values for ResponsesReasoningConfigurationGenerateSummary.
The ResponsesReasoningItem model.
Defines values for ResponsesReasoningItemStatus.
The ResponsesReasoningItemSummaryElement model.
The ResponsesReasoningItemSummaryElementSummaryText model.
Defines values for ResponsesReasoningItemSummaryType.
The ResponsesResponse model.
The ResponsesResponseIncompleteDetails1 model.
Defines values for ResponsesResponseIncompleteDetailsReason.
Defines values for ResponsesResponseStatus.
Emitted when a web search call is completed.
Emitted when a web search call is initiated.
Emitted when a web search call is executing.
The ResponsesResponseUsage model.
The ResponsesResponseUsageOutputTokensDetails model.
The ResponsesStreamEvent model.
Returned when a Response is done streaming.
Emitted when a new content part is added.
Emitted when a content part is done.
Returned when a new Response is created.
Emitted when an error has occurred.
Emitted when in-progress response generation has failed.
Emitted when a file search call is completed (results found).
Emitted when a file search call is initiated.
Emitted when a file search call has begun searching.
Returned when the model-generated function call arguments are updated.
Returned when the model-generated function call arguments are done streaming.
Emitted when response generation has terminated in an incomplete status.
Emitted when the response is in progress.
Returned when a new output item is created during response generation.
Returned when an output item is done streaming.
Emitted when a new output text annotation is added.
Emitted when the text value of a "text" content part is updated.
Emitted when the text value of a "text" content part is done streaming.
Emitted when an incremental delta update to refusal information is available.
Emitted when a refusal output item is completed.
Defines values for ResponsesStreamEventType.
A message item with the `system` role.
The ResponsesTextFormat model.
The ResponsesTextFormatJsonObject model.
The ResponsesTextFormatJsonSchema model.
The ResponsesTextFormatText model.
Defines values for ResponsesTextFormatType.
The ResponsesTool model.
The ResponsesToolChoiceObject model.
The ResponsesToolChoiceObjectComputer model.
The ResponsesToolChoiceObjectFileSearch model.
The ResponsesToolChoiceObjectFunction model.
Defines values for ResponsesToolChoiceObjectType.
The ResponsesToolChoiceObjectWebSearch model.
Defines values for ResponsesToolChoiceOption.
Defines values for ResponsesToolType.
A message item with the `user` role.
The ResponsesWebSearchApproximateLocation model.
The ResponsesWebSearchCallItem model.
Defines values for ResponsesWebSearchCallItemStatus.
Defines values for ResponsesWebSearchContextSize.
The ResponsesWebSearchLocation model.
The ResponsesWebSearchTool model.
The ResponseTextOptions model.
Defines values for ResponseTruncation.
The service tier used for processing the request.
Specifies the latency tier to use for processing the request.
A representation of the request options that control the behavior of a text-to-speech operation.
The supported audio output formats for text-to-speech.
The available voices for text-to-speech.
A structured representation of a stop reason that signifies natural termination by the model.
The Upload object can accept byte chunks in the form of Parts.
Defines values for UploadObject.
The upload Part represents a chunk of bytes we can add to an Upload object.
Defines values for UploadPurpose.
Defines values for UploadStatus.
User security context contains several parameters that describe the AI application itself,
and the end user that interacts with the AI application.