Skip to main content

AI Services Overview

The backend power behind LibreApps Desktop's AI features.

Overview​

The AI Services layer in LibreApps Desktop is responsible for managing interactions with Large Language Models (LLMs). It provides a secure and scalable way to integrate AI into your application, handling everything from prompt engineering to usage tracking.

Key Components​

1. AI Chat Server​

A Python-based microservice that handles conversational AI requests. It manages chat history, context injection, and real-time streaming.

2. LiteLLM Proxy​

A unified interface for connecting to 100+ LLM providers (OpenAI, Anthropic, Google, etc.). It allows you to switch models with a simple configuration change.

3. Model Management​

Tools and configurations for defining which models are available to your users and how they should be used.

4. Usage Tracking​

A system for monitoring and logging AI usage, allowing you to track costs and optimize performance.

Why Use AI Services?​

  • Security: Protect your API keys by keeping them on the backend.
  • Flexibility: Easily switch between different LLM providers without changing your frontend code.
  • Scalability: Handle high volumes of AI requests with a dedicated microservice.
  • Control: Implement custom logic for prompt filtering, rate limiting, and response formatting.

Best Practices​

  • ✅ Do this: Use the AI Chat Server for all conversational features.
  • ✅ Do this: Leverage LiteLLM to experiment with different models and find the best fit for your use case.
  • ❌ Don't do this: Expose your LLM provider API keys directly to the frontend.