zed/docs/src/language-model-integration.md

Language model integration

Assistant Panel

The assistant panel provides you with a way to interact with OpenAI's large language models. The assistant is good for various tasks, such as generating code, asking questions about existing code, and even writing plaintext, such as emails and documentation. To open the assistant panel, toggle the right dock by using the workspace: toggle right dock action in the command palette (cmd-shift-p).

Note

: A default binding can be set to toggle the right dock via the settings.

Setup

1. Create an OpenAI API key

2. Make sure that your OpenAI account has credits

3. Open the assistant panel, using either the assistant: toggle focus or the workspace: toggle right dock action in the command palette (cmd-shift-p).

4. Make sure the assistant panel is focused:

   

5. Open the command palette (cmd-shift-p) and use the now-available assistant: reset key action to set your OpenAI API key:

The OpenAI API key will be saved in your keychain.

Zed will also use the OPENAI_API_KEY environment variable if it's defined. If you need to reset your OpenAI API key, focus on the assistant panel and run the command palette action assistant: reset key.

Having a conversation

The assistant editor in Zed functions similarly to any other editor. You can use custom key bindings and work with multiple cursors, allowing for seamless transitions between coding and engaging in discussions with the language models. However, the assistant editor differs with the inclusion of message blocks. These blocks serve as containers for text that correspond to different roles within the conversation. These roles include:

• You
• Assistant
• System

To begin, select a model and type a message in a You block.

As you type, the remaining tokens count for the selected model is updated.

Inserting text from an editor is as simple as highlighting the text and running cmd-> (assistant: quote selection); Zed will wrap it in a fenced code block if it is code.

To submit a message, use cmd-enter (assistant: assist). Unlike typical chat applications where pressing enter would submit the message, in the assistant editor, our goal was to make it feel as close to a regular editor as possible. So, pressing enter simply inserts a new line.

After submitting a message, the assistant's response will be streamed below, in an Assistant message block.

The stream can be canceled at any point with escape. This is useful if you realize early on that the response is not what you were looking for.

If you want to start a new conversation at any time, you can hit cmd-n or use the New Context menu option in the hamburger menu at the top left of the panel.

Simple back-and-forth conversations work well with the assistant. However, there may come a time when you want to modify the previous text in the conversation and steer it in a different direction.

Editing a conversation

The assistant gives you the flexibility to have control over the conversation. You can freely edit any previous text, including the responses from the assistant. If you want to remove a message block entirely, simply place your cursor at the beginning of the block and use the delete key. A typical workflow might involve making edits and adjustments throughout the conversation to refine your inquiry or provide additional context. Here's an example:

1. Write text in a You block.
2. Submit the message with cmd-enter
3. Receive an Assistant response that doesn't meet your expectations
4. Cancel the response with escape
5. Erase the content of the Assistant message block and remove the block entirely
6. Add additional context to your original message
7. Submit the message with cmd-enter

Being able to edit previous messages gives you control over how tokens are used. You don't need to start up a new context to correct a mistake or to add additional context and you don't have to waste tokens by submitting follow-up corrections.

Some additional points to keep in mind:

• You are free to change the model type at any point in the conversation.
• You can cycle the role of a message block by clicking on the role, which is useful when you receive a response in an Assistant block that you want to edit and send back up as a You block.

Saving and loading conversations

After you submit your first message, a name for your conversation is generated by the language model, and the conversation is automatically saved to your file system in ~/.config/zed/conversations. You can access and load previous messages by clicking on the hamburger button in the top-left corner of the assistant panel.

Using a custom API endpoint for OpenAI

You can use a custom API endpoint for OpenAI, as long as it's compatible with the OpenAI API structure.

To do so, add the following to your Zed settings.json:

{
  "assistant": {
    "version": "1",
    "provider": {
      "name": "openai",
      "type": "openai",
      "default_model": "gpt-4-turbo-preview",
      "api_url": "http://localhost:11434/v1"
    }
  }
}

The custom URL here is http://localhost:11434/v1.

Using Ollama on macOS

You can use Ollama with the Zed assistant by making Ollama appear as an OpenAPI endpoint.

1. Add the following to your Zed settings.json:

{
  "assistant": {
    "version": "1",
    "provider": {
      "name": "openai",
      "type": "openai",
      "default_model": "gpt-4-turbo-preview",
      "api_url": "http://localhost:11434/v1"
    }
  }
}

2. Download, for example, the mistral model with Ollama:

ollama run mistral

3. Copy the model and change its name to match the model in the Zed settings.json:

ollama cp mistral gpt-4-turbo-preview

4. Use assistant: reset key (see the Setup section above) and enter the following API key:

ollama

5. Restart Zed

Using Claude 3.5 Sonnet

You can use Claude with the Zed assistant by adding the following settings:

"assistant": {
  "version": "1",
  "provider": {
    "default_model": "claude-3-5-sonnet",
    "name": "anthropic"
  }
},

When you save the settings, the assistant panel will open and ask you to add your Anthropic API key. You need can obtain this key here.

Even if you pay for Claude Pro, you will still have to pay for additional credits to use it via the API.

Inline generation

You can generate and transform text in any editor by selecting text and pressing ctrl-enter. You can also perform multiple generation requests in parallel by pressing ctrl-enter with multiple cursors, or by pressing ctrl-enter with a selection that spans multiple excerpts in a multibuffer. To create a custom keybinding that prefills a prompt, you can add the following format in your keymap:

[
  {
    "context": "Editor && mode == full",
    "bindings": {
      "ctrl-shift-enter": [
        "assistant::InlineAssist",
        { "prompt": "Build a snake game" }
      ]
    }
  }
]