Azure.AI.Inference Namespace

Model factory for models.

Client options for Azure.AI.Inference library clients.

The representation of a single prompt completion as part of an overall chat completions request. Generally, n choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated.

Representation of the response data from a chat completions request. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data.

The ChatCompletions service client.

A tool selection of a specific, named function tool that will limit chat completions to using the named function.

A tool selection of a specific, named function tool that will limit chat completions to using the named function.

The configuration information for a chat completions request. Completions support a wide variety of tasks and generate text that continues from or "completes" provided prompt data.

Represents the format that the model must output. Use this to enable JSON mode instead of the default text mode. Note that to enable JSON mode, some AI models may also require you to instruct the model to produce JSON via a system or user message. Please note ChatCompletionsResponseFormat is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include ChatCompletionsResponseFormatJSON and ChatCompletionsResponseFormatText.

A response format for Chat Completions that restricts responses to emitting valid JSON objects. Note that to enable JSON mode, some AI models may also require you to instruct the model to produce JSON via a system or user message.

A response format for Chat Completions that emits text responses. This is the default response format.

A function tool call requested by the AI model.

Represents an optional control that specifies which, if any, tools may be called by the model while processing a chat completions request.

The definition of a chat completions tool that can call a function.

An abstract representation of a structured content item within a chat message. Please note ChatMessageContentItem is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include ChatMessageImageContentItem and ChatMessageTextContentItem.

A structured chat content item containing an image reference.

A structured chat content item containing plain text.

A request chat message representing response or action from the assistant.

An abstract representation of a chat message as provided in a request. Please note ChatRequestMessage is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include ChatRequestAssistantMessage, ChatRequestSystemMessage, ChatRequestToolMessage and ChatRequestUserMessage.

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.

Representation of the token counts processed for a completions request. Counts consider all tokens across prompts, choices, choice alternates, best_of generations, and other consumers.

Representation of a single embeddings relatedness comparison.

The Embeddings service client.

The configuration information for an embeddings request.

Representation of the response data from an embeddings request. Embeddings measure the relatedness of text strings and are commonly used for search, clustering, recommendations, and other similar scenarios.

Measurement of the amount of tokens used in this request and response.

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.

Represents some basic information about the AI model.

Represents an update to a single prompt completion when the service is streaming updates using Server Sent Events (SSE). Generally, n choices are generated per provided prompt with a default value of 1. Token limits and other settings may limit the number of choices generated.

Represents an incremental update to a streamed Chat Completions response.

A representation of a chat message update as received in a streaming response.

An update to the function tool call information requested by the AI model.

Represents an incremental update to a streaming function tool call that is part of a streaming chat completions choice.

Represents an operation response with streaming content that can be deserialized and enumerated while the response is still being received.

Represents an incremental update to a streaming tool call that is part of a streaming chat completions choice.

The ChatCompletionsNamedToolChoice_type.

The ChatCompletionsToolCall_type.

Represents a generic policy for how a chat completions tool may be selected.

The ChatCompletionsToolDefinition_type.

A representation of the possible image detail levels for image-based chat completions message content.

A description of the intended purpose of a message within a chat completions interaction.

Representation of the manner in which a completions response concluded.

The format of the embeddings result. Returns a 422 error if the model doesn't support the value or parameter.

Represents the input types used for embedding search.

Controls what happens if extra parameters, undefined by the REST API, are passed in the JSON request payload.

The type of AI model.

The version of the service to use.