Tabby

Integrate Jan with Tabby and Your Favorite IDEs

Tabby is an open-source, self-hosted AI coding assistant. With Tabby, teams can easily set up their own LLM-powered code completion server.

Tabby provides integrations with VSCode, JetBrains, and other IDEs to help developers code more efficiently, and it can be used with various LLM services, including Jan.

To integrate Jan with Tabby, follow these steps:

1. Enable the Jan API Server To set up Tabby with Jan’s Local Server, you must activate the Jan API Server with your chosen model.

   1. Click the Local API Server (<>) button above the Settings. Jan will direct you to the Local API Server section.
   2. Configure the server, including the IP Port, Cross-Origin Resource Sharing (CORS), and Verbose Server Logs.
   3. Press the Start Server button.

2. Find the Model ID and Ensure the Model is Activated

   1. Go to Settings > My Models.
   2. Models are listed with their Model ID beneath their names.
   3. Click the three dots (⋮) button next to the model.
   4. Select Start Model to activate the model.

3. Installing Tabby Server Use the following documentation to install the Tabby server:

   • Docker
   • Apple Silicon
   • Linux
   • Windows Then, follow the steps to connect Jan with the Tabby server: Connect Jan with Tabby. For example, to connect Jan with Tabby, save the following configuration under ~/.tabby/config.toml:

   ~/.tabby/config.toml

   [model.chat.http]
   kind = "openai/chat"
   model_name = "model_id"
   api_endpoint = "http://localhost:1337/v1"
   api_key = ""

   Currently, the Jan completion and embedding API is under construction. Once completed, you can also connect Jan with Tabby for completion and embedding tasks.

4. Installing Tabby on Your Favorite IDEs Refer to the following documentation to install the Tabby extension on your favorite IDEs:

   • Visual Studio Code
   • JetBrains IntelliJ Platform
   • VIM / NeoVIM

How to Use Tabby with Jan Integration

Answer Engine: Chat with Your Codes and Documentation

Tabby offers an Answer Engine on the homepage, which can leverage the Jan LLM and related contexts like code, documentation, and web pages to answer user questions.

Simply open the Tabby homepage at localhost:8080 and ask your questions.

IDE Chat Sidebar

After installing the Tabby extension on your preferred IDEs, you can engage in a conversation with Jan to:

1. Discuss your code, receive suggestions, and seek assistance.
2. Request Jan to inline edit your code, and then review and accept the proposed changes.