Cloud operating system for your business

ChatGPT is an artificial intelligence (AI) chatbot that uses natural language processing to create humanlike conversational dialogue. The language model can...

You can control how many past messages are including in conversation with AI Chat. The more messages you include the more context AI will have about the con...

You can set a limit on the number of tokens per AI Chat response. omniAI supports a maximum of 32768 tokens shared between the prompt (including system mess...

AI Temperature controls randomness. Lowering the temperature means that the AI Chat will produce more repetitive and deterministic responses. Increasing the...

Similar to temperature, this controls randomness but uses a different method. Lowering Probability will narrow the AI Chat’s token selection to likelier tok...

Stop Sequences Stop Sequences are used to make the AI Chat to stop at a desired point, such as the end of a sentence or a list. Generally, the return ke...

Frequency Penalty is between -2.0 and 2.0 and it impacts how the Omni AI penalizes new tokens based on their existing frequency in the text. Positive va...

Presence Penalty is between -2.0 and 2.0 and it impacts how the Omni AI penalizes new tokens based on whether they have appeared in the text so far. Pos...

Generate multiple responses, and display only the one with the best total probability across all its tokens. The unused candidates will still incur usag...

This is an estimate of the number of tokens that will be used for the next request.  1. Response Tokens: The number of tokens generated across all respo...