Package com.azure.ai.openai.assistants.models

Class AssistantsApiResponseFormatOption

java.lang.Object
com.azure.ai.openai.assistants.models.AssistantsApiResponseFormatOption
public final class AssistantsApiResponseFormatOption extends Object
Specifies the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.

  • Constructor Details

    • AssistantsApiResponseFormatOption

      public AssistantsApiResponseFormatOption(AssistantsApiResponseFormatMode mode)
      Creates a new instance of AssistantsApiResponseFormatOption.
      Parameters:
      mode - The mode in which the model will handle the return format of a tool call.

    • AssistantsApiResponseFormatOption

      public AssistantsApiResponseFormatOption(AssistantsApiResponseFormat format)
      Creates a new instance of AssistantsApiResponseFormatOption.
      Parameters:
      format - The format in which the model will handle the return format of a tool call.

  • Method Details

    • getMode

      public AssistantsApiResponseFormatMode getMode()
      Gets the mode in which the model will handle the return format of a tool call.
      Returns:
      The mode in which the model will handle the return format of a tool call.

    • getFormat

      public AssistantsApiResponseFormat getFormat()
      Gets the format in which the model will handle the return format of a tool call.
      Returns:
      The format in which the model will handle the return format of a tool call.

    • fromBinaryData

      public static AssistantsApiResponseFormatOption fromBinaryData(com.azure.core.util.BinaryData responseFormatBinaryData)
      Creates a new instance of AssistantsApiResponseFormatOption based on a JSON string.
      Parameters:
      responseFormatBinaryData - input JSON string
      Returns:
      a new instance of AssistantsApiResponseFormatOption
      Throws:
      IllegalArgumentException - If the provided JSON string does not match the expected format.