Training your AI Chatbot
LooperChat's AI Assistant uses RAG (Retrieval-Augmented Generation) to answer visitor queries based on your specific data. To make the AI effective, you need to configure its "Knowledge Base" via Datasources.
You can train the AI on your existing website content.
Note: You can define Auto-Crawling rules in Project Settings to automatically include or exclude URL patterns.
Add structured Question & Answer pairs for precise responses.
Customize the behavior and personality of your AI Assistant.
Navigate to Projects > Select Project > Data Source > System Prompts.
Prompt: Enter instructions for the AI.
Example: "You are a helpful support agent for Acme Corp. Be polite and concise. Only answer questions related to our products."
Use System Prompt: You can also select from pre-configured system templates if available.
To power the AI, you must connect an AI provider (usually OpenAI) at the organization level.
With datasources and AI configuration in place, LooperChat's AI Assistant is ready to respond to visitors using your own data in a reliable and controlled way.