Skip to content
innFactory AI Dokumentation CompanyGPT Documentation

Settings

The settings can be accessed via the user menu in the lower left corner.

General

Section titled “General”

Basic settings can be configured under General:

general

Design

Section titled “Design”
  • Light
  • Dark
  • System

Display language

Section titled “Display language”

Language in which the user interface is displayed.

User messages as Markdown

Section titled “User messages as Markdown”

Controls the display of user messages as Markdown. Markdown is a lightweight syntax for marking up text. AIs also respond in Markdown, and the content is displayed accordingly (e.g., bold). This setting controls whether user messages should also be displayed in this format.

Automatically scroll to the latest message

Section titled “Automatically scroll to the latest message”

This setting controls whether existing chats should automatically scroll to the bottom to the latest message when they are opened.

Hide right sidebar

Section titled “Hide right sidebar”

Permanently hide the right sidebar.

Archived chats

Section titled “Archived chats”

View archived chats with the option to restore or permanently delete them.

Chat

Section titled “Chat”

Font size

Section titled “Font size”

Select the font size in which chat messages should be displayed.

Chat direction

Section titled “Chat direction”
  • ltr: Left to right
  • rtl: Right to left

Press Enter to send messages

Section titled “Press Enter to send messages”

When enabled, Enter is sufficient to send messages. New lines can be added with Shift + Enter. When disabled, Ctrl / Cmd + Enter must be used to send messages, Enter then adds a new line.

Center chat input on the welcome screen

Section titled “Center chat input on the welcome screen”

Chat input is centered or centered at the bottom on the welcome screen.

Open thought process dropdowns by default

Section titled “Open thought process dropdowns by default”

When AI models are thinking, the thought process can be displayed by default or hidden behind a dropdown and opened when needed.

Always show code when using the code interpreter

Section titled “Always show code when using the code interpreter”

Code is displayed by default.

Parse LaTeX in messages (may affect performance)

Section titled “Parse LaTeX in messages (may affect performance)”

When enabled, LaTeX code in messages is rendered as mathematical equations. Disabling this may improve performance if LaTeX rendering is not required.

Save drafts locally

Section titled “Save drafts locally”

When enabled, text and attachments entered into the chat form are automatically saved locally as drafts. These drafts are also available when the page is reloaded or when switching to another conversation. Drafts are stored locally on the device and are deleted once the message is sent.

Commands

Section titled “Commands”

Commands are shortcuts that can be executed in the message input field, allowing quick access to models, prompts, and multiple responses.

@ command for switching models

Section titled “@ command for switching models”

Toggles the “@” command for switching endpoints, models, presets, etc.

Command + for multiple responses

Section titled “Command + for multiple responses”

Toggles the “+” command to add a multiple response setting.

Command / for prompt template

Section titled “Command / for prompt template”

Toggles the “/” command to select a prompt template via the keyboard.

Language

Section titled “Language”

Both speech-to-text (STT) and text-to-speech (TTS) are available in CompanyGPT. Both can be used via the integrated browser engine as well as via LLMs (the LLMs must be configured accordingly).

Speech-to-text

Section titled “Speech-to-text”

Can be used to dictate prompt inputs instead of typing.

Engines:

  • External: LLM
  • Browser: Engine of the current browser

Language: The language of the input

Automatically transcribe audio

Automatically send text

Text to Speech

Section titled “Text to Speech”

Can be used to have messages read aloud.

Engines:

  • External: LLM
  • Browser: Engine of the current browser

Voice: Available voices, either from the browser engine or AI

Personalization

Section titled “Personalization”

Use saved memories

Section titled “Use saved memories”

Allow the AI to access and use your saved memories when responding.

Data control

Section titled “Data control”

Import conversations

Section titled “Import conversations”

Conversations can be imported from an exported JSON file, for example, to share them with colleagues.

Section titled “Shared links”

View conversations shared via links. The links can be accessed again, the source chats can be opened, or the shared links can be deleted.

User API keys

Section titled “User API keys”

If AI API keys have been assigned at the user level, they can be revoked here.

TTS cache memory

Section titled “TTS cache memory”

The TTS cache memory can be cleared if it is used.

Delete all chats

Section titled “Delete all chats”

Delete all chats.

Account

Section titled “Account”

Show usernames in messages

Section titled “Show usernames in messages”

When enabled, the sender’s username will be displayed above each message that is sent. When disabled, “You” will be displayed above the messages.

Profile picture

Section titled “Profile picture”

Change profile picture

Delete account

Section titled “Delete account”

Delete user account