AssistantCreateRequest property. Gets or sets the format that the model must output. Compatible with GPT4o GPT4 Turbo and all GPT3.5 Turbo models since gpt3.5turbo1106 . 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 longrunning and seemingly stuck request. Also note that the message content may be partially cut off if finish_reasonlength which indicates the generation exceeded max_tokens or the conversation exceeded the max context length...Setting to { “type”: “json_object” } enables JSON mode, which guarantees...generates is valid JSON. Important: when using JSON mode, you must...