AI Assistant
Ask the bot anything with /ask.
Overview
/ask — an AI assistant that answers questions about the bot and server. Uses RAG (Retrieval-Augmented Generation) to search documentation. Prompt injection protection: 20+ blocking patterns.
How to Use
Command: /ask question:<your question> Max question length: 500 characters. Response comes as an ephemeral message (only visible to the author).
RAG — Document Search
The bot indexes server documents into a vector database: • Documents split into chunks (800 chars, 100 overlap) • Embeddings created via Ollama (nomic-embed-text) • On question, similar chunks are found (cosine similarity, threshold 0.7) • Found context is added to the prompt Indexing: Dashboard → AI → Index Documents.
Models
Models and token limits by subscription tier: • Free — Groq llama-3.3-70b-versatile (200 tokens) • Pro — Groq llama-3.3-70b-versatile (1000 tokens) • Business — Groq llama-3.3-70b-versatile (2000 tokens) or BYOK provider Provider cascade (when Groq is unavailable): Groq → Cerebras (qwen-3-235b) → Ollama (local). Business tier supports BYOK: OpenAI, Anthropic, or any OpenAI-compatible provider.
Limits & Cooldowns
Daily request limits: • Free — 10 requests/day • Pro — 50 requests/day • Business — unlimited Cooldown between requests: • Free — 60 seconds • Pro — 10 seconds • Business — 5 seconds
For Administrators
Dashboard → AI: • Enable/disable the module • Index documents • Query and response log • Usage statistics
Configure modules in-Discord with the menu-first admin panel — no slash commands needed.