FinishReason

STOP is the most common finish reason, and it occurs when the model completely generates its entire message, and has nothing else to add. Ideally, you always want your finish reason to be STOP.

Occurs when ChatGPT is not able to finish the response within the token limit. When the model reaches the token limit, it returns the incomplete message with finish reason LENGTH. Some models have a higher token limit than others.

Occurs due to a flag from OpenAI's content filters. This occurrence is rare, and tends to happen when you blatantly violate OpenAI's terms.

Occurs when the model uses one of the available tools.

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Returns an array containing the constants of this enum type, in the order they're declared.