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.
It’s async and fast, streams responses.
Interact with ChatGPT from anywhere in Emacs (any buffer, shell, minibuffer, wherever)
ChatGPT’s responses are in Markdown or Org markup.
Supports conversations and multiple independent sessions.
Save chats as regular Markdown/Org/Text files and resume them later.
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.

Breaking Changes
Installation
- Straight
- Manual
- Doom Emacs
- Spacemacs
Usage
- In any buffer:
- In a dedicated chat buffer:
Using it your way
- Extensions using GPTel
Additional Configuration
Why another ChatGPT client?
Will you add feature X?
Alternatives
Acknowledgments

Breaking Changes

gptel-api-key-from-auth-source now searches for the API key using the value of gptel-host, i.e. “api.openai.com” instead of the original “openai.com”. You need to update your ~/.authinfo.

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, “api.openai.com” is used as HOST and “apikey” as USER.
```
machine api.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.

Save and restore your chat sessions

Saving the file will save the state of the conversation as well. To resume the chat, open the file and turn on gptel-mode before editing the buffer.

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.

Extensions using GPTel

These are packages that depend on GPTel to provide additional functionality

gptel-extensions: Extra utility functions for GPTel.
ai-blog.el: Streamline generation of blog posts in Hugo.

Additional Configuration

gptel-host: Overrides the OpenAI API host. This is useful for those who transform Azure API into OpenAI API format, utilize reverse proxy, or employ third-party proxy services for the OpenAI API.
gptel-proxy: Path to a proxy to use for GPTel interactions. This is passed to Curl via the --proxy argument.

Why another ChatGPT client?

Other Emacs clients for ChatGPT prescribe the format of the interaction (a comint shell, org-babel blocks, etc). I wanted:

Something that is as free-form as possible: query ChatGPT using any text in any buffer, and redirect the response as required. Using a dedicated gptel buffer just adds some visual flair to the interaction.
Integration with org-mode, not using a walled-off org-babel block, but as regular text. This way ChatGPT can generate code blocks that I can run.

Will you add feature X?

Maybe, I’d like to experiment a bit more first. Features added since the inception of this package include

Curl support (gptel-use-curl)
Streaming responses (gptel-stream)
Cancelling requests in progress (gptel-abort)
General API for writing your own commands (gptel-request, wiki)
Dispatch menus using Transient (gptel-send with a prefix arg)
Specifying the conversation context size
GPT-4 support
Response redirection (to the echo area, another buffer, etc)
A built-in refactor/rewrite prompt
Limiting conversation context to Org headings using properties (#58)
Saving and restoring chats (#17)

Features being considered or in the pipeline:

Fully stateless design (#17)

Alternatives

Other Emacs clients for ChatGPT include

chatgpt-shell: comint-shell based interaction with ChatGPT. Also supports DALL-E, executable code blocks in the responses, and more.
org-ai: Interaction through special #+begin_ai ... #+end_ai Org-mode blocks. Also supports DALL-E, querying ChatGPT with the contents of project files, and more.

There are several more: chatgpt-arcana, leafy-mode, chat.el

Acknowledgments

Alexis Gallagher and Diego Alvarez for fixing a nasty multi-byte bug with url-retrieve.
Jonas Bernoulli for the Transient library.

janEbert/gptel