小渔分享

Integration of Translation Tools with AI Large Models#

— First Method: API Call Free Large Model OpenRouter#

• OpenRouter

  • https://openrouter.ai/
  • You can log in with a GitHub account, Google account, or MetaMask account

• Obtain Private Key

  

• Model Address

  • https://openrouter.ai/models?max_pric...
    nousresearch/hermes-3-llama-3.1-405b
    google/gemini-pro-1.5-exp
    meta-llama/llama-3.2-11b-vision-instruct (choose a suitable model from this address)

• Immersive Translation Configuration

  

  

• openai-translator Translation Tool

  

  

— Second Method: Local Deployment —#

• Ollama
  • Download Address
    • https://ollama.com/
  • Installation
    • Refer to previous videos
  • Ollama Server
    • Ollama API
      • http://127.0.0.1:11434
    • OpenAi API
      • http://127.0.0.1:11434/v1/chat/completions
  • Intranet Access Configuration, how to access via http://127.0.0.1:11434 **** without configuration.

    • Environment Variables → User Variables Add

      Copy

      OLLAMA_ORIGINS=*
      OLLAMA_HOST=0.0.0.0:11434
      

    • After configuration, you can access via the intranet IP, for example:

      • http://192.168.0.1:11434
• Models Models

  • gemma3

    • Gemma is a lightweight model series built by Google based on Gemini technology
    • Gemma 3 offers 1B, 4B, 12B, and 27B parameters

  • Ollama Download gemma3 (My device is Mac mini M4)

    

    Copy

    ollama run gemma3:4b or ollama pull gemma3:4b
    

  • View Installed Models

    Copy

    ollama list
    

  • Browser Access Address

    • http://127.0.0.1:11434
• Immersive Translation Configuration

  • Translation Service, Add OpenAi Compatible Service: Model gemma3:4b

    

  • Translation Service, Add OpenAi Compatible Service: Model deepseek-r1:7b