a

(optional) Freely assignable session key. If nothing is specified here, a fixed internal session key is used. With individual session keys, multiple instances of ChatGPT sessions can be built up, where each instance has its own prompt and chat history. After the end of phase 3, all instances are removed (also the internal one).

b

"true", if the session is to be established via a DMZ server (if available). Default: "false".

c

Your API URL. Example: "https://<your-resource-name>.openai.azure.com/openai/deployments/<deployment-id>/chat/completions".

<your-resource-name> - The name of your Azure OpenAI Resource.

<deployment-id> - The deployment name you chose when you deployed the model.

d

(optional) The API version . Example: " 2023-03-15-preview".

e

Your API key .

f

The sampling temperature. Higher values will make the output more random/creative, while lower values will make it more focused and deterministic. Allowed values: " 0.1" to " 1" .

g

The maximum number of tokens to generate in the chat completion . Allowed values : " 1" to " 4096" .

h

(optional) Content for the role " system" . Example: You are a database SQL expert and answer questions related to SQL statements.