Skip to content

Chat Interface

The Chat Interface is where you interact with AI models. It is designed to be intuitive yet powerful, supporting rich text rendering, code highlighting, and advanced features like reasoning visualization.

Overview

The interface consists of three main areas:

  1. Message History: The central area displaying the conversation.

  2. Input Area: At the bottom, where you type your messages.

  3. Control Bar: At the top, showing the current model and providing access to parameters.

Rich Text & Code

Backend.AI GO supports full Markdown rendering.

  • Code Blocks: Automatically detects programming languages and applies syntax highlighting. You can copy code with a single click.

  • Mathematics: Supports LaTeX rendering for mathematical formulas (e.g., \(E = mc^2\)).

  • Tables: Renders clean, readable tables from data.

Advanced Chat Features

Message Editing & Forking

You can edit any past message (both yours and the AI's) to steer the conversation in a new direction.

  1. Hover over a message and click the Edit (Pencil) icon.

  2. Modify the text and click Save & Submit.

  3. This creates a Fork (or branch) in the conversation tree. The original message is preserved.

When you edit a message or regenerate a response, you create multiple versions of the conversation at that point.

  • Look for navigation arrows (e.g., < 2 / 3 >) below the message bubble.

  • Click the arrows to switch between different branches of the conversation history. This allows you to explore "what if" scenarios without losing your previous context.

Regenerate Response

If the AI's answer isn't quite right, click the Regenerate (Refresh) icon below the AI's message. This will generate a new response, creating a new branch.

Thinking Blocks (Reasoning Models)

When using advanced "Reasoning Models" like DeepSeek-R1 or Qwen3-Thinking, the model outputs its internal thought process before the final answer.

  • Collapsible View: By default, the thinking process is collapsed to keep the chat clean.

  • Expand to Learn: Click the "Thinking" header (with the brain icon) to expand and read how the model arrived at its conclusion. This is great for debugging logic or understanding complex derivations.

  • Streaming: You can watch the thoughts appear in real-time as the model generates them.

Reasoning Effort Control

You can control how much "thinking" a reasoning model does using the Reasoning Effort control in the chat input area.

  • None (Off): Disables extended thinking. The model responds directly without showing internal reasoning.

  • Low / Medium / High / Extra High: Progressively increases the depth of reasoning. Higher values allow the model to think longer and more thoroughly, which can improve answer quality for complex problems.

  • Default Setting: Configure the default reasoning effort level in Settings > Inference > Default reasoning effort. You can also choose "Last used" to automatically remember and apply the most recently used setting.

Tool Use & Attachments

Tool Calling Visualization

If you are in Agent Mode, the AI may use tools (like Web Search).

  • Transparent Actions: When a tool is called, a special block appears showing what tool was called and with what inputs.

  • Results: Once the tool finishes, you can see the result (e.g., the search results or file content) that was fed back to the AI.

File Attachments

You can drag and drop images into the chat input area to analyze them with multimodal models (like Llama 3.2 Vision, GPT-4o).