Skip to main content

AI Chat

Conversational intelligence for your dashboard.

Overview​

The AI Chat feature provides a powerful and flexible interface for interacting with various AI models. It's designed to be a versatile assistant that can help users with a wide range of tasks, from answering questions to generating content and automating workflows.

Key Features​

  • Multi-Model Support: Switch between different AI models (e.g., GPT-4, Claude, Gemini) to find the best one for your task.
  • Streaming Responses: Real-time message delivery for a smooth and responsive user experience.
  • Context Awareness: The AI can be provided with relevant page context, allowing it to give more accurate and helpful answers.
  • Chat History: Automatically save and manage your chat history, allowing you to pick up where you left off.
  • File Uploads: Upload documents and images for the AI to analyze and discuss.

How it Works​

  1. User Input: The user types a message into the chat interface.
  2. Request to Backend: The frontend sends the message, along with any relevant context, to LibreApps Desktop AI Chat Server.
  3. Model Interaction: The AI Chat Server uses LiteLLM to communicate with the selected AI model provider.
  4. Streaming Response: The model's response is streamed back to the frontend and displayed to the user in real-time.
  5. History Storage: The conversation is saved to the database for future reference.

Customization​

You can customize the AI Chat experience by:

  • Configuring System Prompts: Define the AI's personality and behavior using the Prompt Editor.
  • Adding Custom Tools: Extend the AI's capabilities by providing it with access to your own APIs and data sources.
  • Changing the UI: Customize the appearance of the chat widget to match your brand.

Best Practices​

  • ✅ Do this: Provide clear and concise system prompts to guide the AI's behavior.
  • ✅ Do this: Use context awareness to make the AI's responses more relevant to the user's current task.
  • ❌ Don't do this: Rely on the AI for critical decisions without human oversight; always verify the AI's output.