zalox/openai-api.el

An Emacs interface to OpenAI's language model API.

OpenAI API

A WIP Emacs interface to OpenAI’s language model REST API.

This is intended to be used as a library for building interfaces to the language models.

NOTE: Usage requires an OpenAI API Key. Codex models (for generating code) currently require private beta access.

Installation

use-package example:

(use-package openai-api
  :straight (openai-api :type git :host github :repo "dangirsh/openai-api.el")
  :config
  ;; required
  (setq openai-api-secret-key <token>) ; https://beta.openai.com/account/api-keys
  ;; optional
  (setq openai-api-engine "davinci-codex") ; *-codex models require private beta access
  (setq openai-api-completion-params '((max_tokens . 100)
                                       (temperature . 0.0)
                                       (frequency_penalty . 0)
                                       (presence_penalty . 0)
                                       (n . 1))))

Dependencies

• Request.el – Easy HTTP request for Emacs Lisp

Example Usages

Interactively

Complete the Region: openai-api-complete-region

Currently, there’s only a basic interface that uses the active region as the prompt. Use like this:

1. Set openai-api-completion-params as necessary
2. In any buffer, select the text you’d like to send as a prompt.
3. Run openai-api-complete-region (bind to a key for convenience).

If only one completion is returned (n = 1), it is inserted below the region.

If there are multiple completions returned (n > 1), the built-in completing-read mechanism is used. I recommend trying consult for an improved completing-read interface, which includes live previews.

Programmatically

List all available engines: openai-api-get-engines

(openai-api-get-engines)

("ada" "babbage" "content-filter-alpha" "curie" "curie-instruct-beta" "cushman-codex" "davinci" "davinci-codex" "davinci-instruct-beta")

Request completions for prompt: openai-api-get-completions

(let ((openai-api-completion-params '((max_tokens . 2)
                                       (temperature . 0.0)
                                       (frequency_penalty . 0)
                                       (presence_penalty . 0)
                                       (n . 1))))
  (car (openai-api-get-completions "2 + 2 =")))

"4"

Notes

• I’ve only tested this on GNU Emacs 28.0.50.
• This API tries to prevent unnecessarily wasteful requests. Right now, that means preventing requests that have n>1 and temperature=0.0 (multiple identical results).

Related packages

• debanjum/codex-completion: Generate, Complete Code in Emacs using Op…
• semiosis/pen.el: pen.el is a package for prompt engineering in emacs…

Ideas / Future Work

(some of these should go in separate libraries)

• Generate prompt headers. E.g. Inject a comment with mode-name to indicate the language.
• Better ways to tweak model parameters.
  • e.g. add a prefix arg to openai-api-complete-region to specify number of completion results n.
    • C-u <n> openai-api-complete-region
  • e.g. re-run previous request, but with larger max-token parameter

  -

• Add async / streaming interface
• Integrate with jrosdahl/fancy-dabbrev for greyed-out inline completions (similar to Copilot interface)
• Allow specification of unit tests for generated function
  • filter results based on test results