Interface ChatVisionInput

ChatVisionInput represents the full potential input options for Vision chat.

interface ChatVisionInput {
    image: Base64Encoder;
    inputExtension: InputExtension;
    maxTokens: number;
    model: string;
    outputExtension: OutputExtension;
    question: string;
    role: Roles;
    temperature: number;
    topK: number;
    topP: number;
}

Properties

image represents an object that knows how to retrieve an image.

inputExtension: InputExtension

inputExtension represents a set of optional pre-processing integrations.

maxTokens: number

maxTokens represents the max number of tokens to return.

model: string

model represents the model to use.

outputExtension: OutputExtension

inputExtension represents a set of optional post-processing integrations.

question: string

question represents the question about the image.

role: Roles

role represents the role of the sender (user or assistant).

temperature: number

temperature represents the randomness in GPT's output.

topK: number

topK represents the variability of the generated text.

topP: number

topP represents the diversity of the generated text.