GPTel: A simple ChatGPT client for Emacs

GPTel is a simple, no-frills ChatGPT client for Emacs.

intro-demo.mp4

intro-demo-2.mp4

Requires an OpenAI API key.
Async and fast (streams responses).
Interact with ChatGPT from any buffer in Emacs.
ChatGPT’s responses are in Markdown or Org markup (configurable).
Supports conversations (not just one-off queries) and multiple independent sessions.
You can go back and edit your previous prompts, or even ChatGPT’s previous responses when continuing a conversation. These will be fed back to ChatGPT.

GPTel uses Curl if available, but falls back to url-retrieve to work without external dependencies.

Installation

GPTel is on MELPA. Install it with M-x package-install⏎ gptel.

(Optional: Install markdown-mode.)

Straight

(straight-use-package 'gptel)

Installing the markdown-mode package is optional.

Manual

Clone or download this repository and run M-x package-install-file⏎ on the repository directory.

Installing the markdown-mode package is optional.

Doom Emacs

In packages.el

(package! gptel)

In config.el

(use-package! gptel
 :config
 (setq! gptel-api-key "your key"))

Spacemacs

After installation with M-x package-install⏎ gptel

Add gptel to dotspacemacs-additional-packages
Add (require 'gptel) to dotspacemacs/user-config

Usage

Procure an OpenAI API key.

Optional: Set gptel-api-key to the key. Alternatively, you may choose a more secure method such as:

Storing in ~/.authinfo. By default, “openai.com” is used as HOST and “apikey” as USER.
```
machine openai.com login apikey password TOKEN
    
```
Setting it to a function that returns the key.

In any buffer:

Select a region of text and call M-x gptel-send. The response will be inserted below your region.
You can select both the original prompt and the response and call M-x gptel-send again to continue the conversation.
Call M-x gptel-send with a prefix argument to

set chat parameters (GPT model, directives etc) for this buffer,
to read the prompt from elsewhere or redirect the response elsewhere,
or to replace the prompt with the response.

With a region selected, you can also rewrite prose or refactor code from here:

Code:

Prose:

In a dedicated chat buffer:

Run M-x gptel to start or switch to the ChatGPT buffer. It will ask you for the key if you skipped the previous step. Run it with a prefix-arg (C-u M-x gptel) to start a new session.
In the gptel buffer, send your prompt with M-x gptel-send, bound to C-c RET.
Set chat parameters (GPT model, directives etc) for the session by calling gptel-send with a prefix argument (C-u C-c RET):

That’s it. You can go back and edit previous prompts and responses if you want.

The default mode is markdown-mode if available, else text-mode. You can set gptel-default-mode to org-mode if desired.

Using it your way

GPTel’s default usage pattern is simple, and will stay this way: Read input in any buffer and insert the response below it.

If you want custom behavior, such as

reading input from or output to the echo area,
or in pop-up windows,
sending the current line only, etc,

GPTel provides a general gptel-request function that accepts a custom prompt and a callback to act on the response. You can use this to build custom workflows not supported by gptel-send. See the documentation of gptel-request, and the wiki for examples.

Additional Configuration

You can override the OpenAI API endpoint by customizing gptel-openai-endpoint.

Why another ChatGPT client?

Existing Emacs clients don’t reliably let me use it the simple way I can in the browser. They will get better, but I wanted something for now.

Also, AI-assisted work is a new way to use Emacs. It’s not yet clear what the best Emacs interface to tools like it is.

Should it be part of CAPF (completions-at-point-functions)?
A dispatch menu from anywhere that can act on selected regions?
A comint/shell-style REPL?
One-off queries in the minibuffer (like shell-command)?
A refactoring tool in code buffers?
An org-babel interface?

Maybe all of these, I don’t know yet. As a start, I wanted to replicate the web browser usage pattern so I can build from there – and don’t need to switch to the browser every time. The code is fairly simple right now.

Will you add feature X?

Maybe, I’d like to experiment a bit first.

christianromney/gptel