# Models and Features

<details open>

<summary><mark style="color:orange;"><strong>Which AI models does Qolaba support?</strong></mark></summary>

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.

</details>

<details open>

<summary><mark style="color:orange;"><strong>Can I use multiple AI models in one session?</strong></mark></summary>

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.

</details>

<details open>

<summary><mark style="color:orange;"><strong>What is the difference between a Chatbot and an Agent?</strong></mark></summary>

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.

</details>

<details open>

<summary><mark style="color:orange;"><strong>What files can I upload to a Knowledge Base?</strong></mark></summary>

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.

</details>

<details open>

<summary><mark style="color:orange;"><strong>Does the chatbot have memory between sessions?</strong></mark></summary>

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.

</details>

<details open>

<summary><mark style="color:orange;"><strong>Can I generate images inside the Chatbot?</strong></mark></summary>

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

</details>

<details open>

<summary><mark style="color:orange;"><strong>What is Magic Prompt?</strong></mark></summary>

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.

</details>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.qolaba.ai/faqs/models-and-features.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.