For the complete documentation index, see llms.txt. This page is also available as Markdown.
Chat Agents
The Chatbot widget is a conversational AI interface and processing engine that interacts with your users. To process and generate text, the widget integrates with a configurable large language model (LLM) provider of your choice. It formulates intelligent answers by drawing context from multiple configurable sources, including selected knowledge bases, web searches, MCP servers, and attachments that users upload during the chat. The Chatbot widget powers AI-driven knowledge assistants tailored for customer support, documentation navigation, and internal operations.
In the LLM Provider list, select the provider for your large language model. The default provider is OpenAI.
5
In the Model list, select the specific model that you want the chatbot to use.
The default model is GPT-5.5.
6
Optional: In the Initial prompt field, enter the first assistant message to display when the chat window opens, or leave the field empty to skip the greeting.
7
In the System Prompt field, enter the instructions or persona details that guide the chatbot's behavior.
8
To provide context, select one or more knowledge bases in the Knowledge Base list. To select multiple knowledge bases, press Control (or Command on macOS), and then click the items.
9
Optional: To add a new server configuration, click Add MCP Server.
10
Optional: To allow the chatbot to retrieve information from the internet, turn on the Enable web search toggle.
11
Click Save Config.
12
In the Type a message... field, enter your question or prompt.
13
Optional: To add a file to your message, click .
14
Click or press enter to submit.
15
Optional: To start a new conversation, click New Chat.
16
Optional: To view your previous conversations, click History.
17
Optional: To categorize the conversation, click Tags.
In the Edit Tags dialog, enter a tag name in the Tags field.
