inputExtension represents a set of optional pre-processing integrations.
maxTokens represents the max number of tokens to return.
messages represents the set of messages to process.
model represents the model to use.
onMessage represents a function that will receive the messages.
temperature represents the randomness in GPT's output.
topK represents the variability of the generated text.
topP represents the diversity of the generated text.
ChatSSEInput represents the full potential input options for SSE chat.