Enable your own AI llama copilot

With open source and self hosted technologies

Ollama

Ollama is an open-source project that enables users to run large language models (LLMs) locally on their machines.

Ollama install

curl -fsSL https://ollama.com/install.sh | sh

Continue VsCode Plugin

Install Continue

Ollama run models

ollama run deepseek-coder:6.7b-base
ollama run llama3:8b
ollama pull nomic-embed-text

Configuration file for Continue

{
  "models": [
    {
      "title": "Llama 3 8B",
      "provider": "ollama",
      "model": "llama3:8b"
    }
  ],
  "tabAutocompleteModel": {
    "title": "DeepSeek Coder 6.7B",
    "provider": "ollama",
    "model": "deepseek-coder:6.7b-base"
  },
    "embeddingsProvider": {
    "provider": "ollama",
    "model": "nomic-embed-text"
  }
}

Image Continue Interface

Useful Commands

Easily understand code sections
ctrl+L
Tab to autocomplete code suggestions
ctrl+space
Refactor functions where you are coding
ctrl+
Ask questions about your codebase
@codebase 
Quickly use documentation as context
@docs