Skip to main content

Continue

How to Integrate with Continue VS Code​

Continue is an open-source autopilot compatible with Visual Studio Code and JetBrains, offering the simplest method to code with any LLM (Local Language Model).

To integrate Jan with a local AI language model, follow the steps below:

Step 1: Installing Continue on Visal Studio Code​

Follow this guide to install the Continue extension on Visual Studio Code

Step 2: Enable the Jan API Server​

To set up Continue for use with Jan's Local Server, you must activate the Jan API Server with your chosen model.

  1. Press the <> button. Jan will take you to the Local API Server section.

  2. Setup the server, which includes the IP Port, Cross-Origin-Resource-Sharing (CORS) and Verbose Server Logs.

  3. Press the Start Server button

Step 3: Configure Continue to Use Jan's Local Server​

  1. Go to the ~/.continue directory.
cd ~/.continue
~/.continue/config.json
{
  "models": [
    {
      "title": "Jan",
      "provider": "openai",
      "model": "mistral-ins-7b-q4",
      "apiKey": "EMPTY",
      "apiBase": "http://localhost:1337"
    }
  ]
}
  1. Ensure the file has the following configurations:
    • Ensure openai is selected as the provider.
    • Match the model with the one enabled in the Jan API Server.
    • Set apiBase to http://localhost:1337.
    • Leave the apiKey field to EMPTY.

Step 4: Ensure the Using Model Is Activated in Jan​

  1. Navigate to Settings > Models.
  2. Activate the model you want to use in Jan by clicking the three dots (⋮) and select Start Model.

Try out Jan integration with Continue in Visual Studio Code​

1. Asking questions about the code​

  1. Highlight a code snippet and press Command + Shift + M to open the Left Panel.
  2. Select Jan at the bottom and ask a question about the code, for example, Explain this code.

2. Editing the code with the help of a large language model​

  1. Select a code snippet and use Command + Shift + L.
  2. Enter your editing request, such as Add comments to this code.