Chat
This module asks questions about the content. The answers are displayed in the AI tab, after the content summary.
Setting up the AI service is described on the Mistral integration page.
Server access configuration: server access module that holds the location of the service and its authentication information, centralized for every application. It must hold the configuration of an AI server.
A.I. model: AI model chosen in the list.
Configure temperature: sets the variability of the AI answers: high, it diversifies them. Low, it makes them more predictable.
Temperature: number between 0 and 10 (7 by default).
Context and instructions for A.I.: context passed to the AI. It helps the engine understand the kind of content processed and tunes the way the chat answers. Since the chat uses the language of the current user, it must be configured in each language used.
Maximum words to the generated answer: length past which the answer is truncated.
The "Test model" button opens a window to pass a text and get the result live with the model and the module as configured. A Question field chats with the model.