Models and Features

Which AI models does Qolaba support?

Qolaba supports 60+ models across text, image, video, speech, and music. LLM providers include OpenAI (GPT-4o, GPT-5), Anthropic (Claude Sonnet 4, Claude Opus 4.5), Google (Gemini 2.5 Pro, Gemini 3 Pro), DeepSeek, xAI (Grok 4), and Perplexity. See Section 17 for the full reference list.

Can I use multiple AI models in one session?

Yes. You can switch models at any time via the model selector in the Chatbot. Each conversation uses the selected model for that session. You can start a new chat to switch models cleanly.

What is the difference between a Chatbot and an Agent?

The Chatbot is the general-purpose conversation interface where you select a model and prompt freely. An Agent is a persistent configuration — a named persona with defined instructions, a specific model, and optionally an attached Knowledge Base. Agents ensure consistent role-based behaviour across all sessions they are used in.

What files can I upload to a Knowledge Base?

Supported formats: PDF, DOCX, TXT, images (JPG, PNG), and URLs. File size limits: up to 1,000 pages or 200 MB per document. Images: up to 20 MB per file. URLs: up to 20 per Knowledge Base.

Does the chatbot have memory between sessions?

The Chatbot does not maintain memory between separate conversations. Each new chat starts fresh. To persist context across sessions, create a Custom Agent with defined system instructions, or use a Knowledge Base — both carry structured context into every conversation they are attached to.

Can I generate images inside the Chatbot?

Yes. Enable the 'Image Generation' toggle in the Toolkit to generate images directly within a chat conversation.

What is Magic Prompt?

Magic Prompt is an AI-assisted prompt enhancement tool available in Text to Image and Image to Image. It automatically expands your short input into a detailed, model-optimised prompt — improving output quality without requiring advanced prompt engineering knowledge.