Skip to main content

🤖 emlog Integration with LLMs and AI Applications

Configure AI​

The latest version of the emlog system supports configuring AI LLMs, allowing easy integration with models like DeepSeek and OpenAI. In the backend, click on the left system menu - Settings - AI to complete the addition of AI LLMs and start experiencing AI functions such as conversation, text generation, and image generation.

Text Chat Models​

The system supports adding OpenAI protocol LLMs. Configuration examples for well-known LLMs are as follows:

OpenAI​

  • API URL: https://api.openai.com/v1/chat/completions
  • API Key: Generate API Key, format: sk-****
  • Model:
    • gpt-5-2025-08-07
    • gpt-5-mini-2025-08-07
    • gpt-4.1-2025-04-14
    • gpt-4o-2024-11-20
    • All Models

Google Gemini​

  • API URL: https://generativelanguage.googleapis.com/v1beta/openai/chat/completions
  • API Key: Generate API Key
  • Model:
    • gemini-2.0-flash
    • gemini-2.5-pro-preview-06-05

Claude​

  • API URL: https://api.anthropic.com/v1/messages
  • API Key: Generate API Key
  • Model:
    • claude-sonnet-4-20250514
    • claude-3-7-sonnet-20250219
    • claude-3-5-sonnet-20241022

Grok​

  • API URL: https://api.x.ai/v1/chat/completions
  • API Key: Generate API Key
  • Model:
    • grok-4-0709
    • grok-3
    • grok-3-fast
    • grok-3-mini

Image Generation Models​

OpenAI DALL-E​

  • API URL: https://api.openai.com/v1/images/generations
  • API Key: Generate API Key, format: sk-****
  • Model:
    • dall-e-3

FAQ​

Why is the AI conversation response slow?​

  1. It may be a problem with the AI model provider. You can try switching to an AI model from another service provider.
  2. It may be a server network problem. The AI interface requests are relayed through the server. If the network is unstable, it will cause delays.