iTerm2 Ollama Integration

iTerm2-Ollama-Integration.md

iTerm2 Ollama Integration

A guide on using Ollama as the OpenAI API provider for inline completions in iTerm2.

Configuration

• API URL: http://127.0.0.1:11434/v1/completions
• Model: mistral
• Tokens: 4000
• Use legacy completions API: true

Prompt

Return commands suitable for copy/pasting into \(shell) on \(uname).

The script should do this: \(ai.prompt)

IMPORTANT: Do NOT include any instructions, bullet points, commentary NOR Markdown triple-backtick code blocks as your whole response will be copied into my terminal automatically. ONLY return the command without enclosing it in a Markdown code block.

I am using below,

• Enable Generative AI Features
  True
• OpenAI API Key:

  ollama
  

• API URL:

  http://localhost:11434/v1/chat/completions
  

• Model:

  llama3.2:latest
  

• Tokens:

  99,999
  

• Use legacy completions API:
  False

@bsahane tried your config but used the mistral:latest for the model. Works like a charm!