chatgpt-api/docs

chatgpt / Exports

ChatGPT API

Node.js wrapper around ChatGPT. Uses headless Chrome as a temporary solution until the official API is released.

• Intro
• Auth
• Usage
• Docs
• Todo
• Related
• License

Intro

This package is a Node.js TypeScript wrapper around ChatGPT by OpenAI.

Auth

It uses headless Chromium via Playwright under the hood, so you still need to have access to ChatGPT, but it makes it much easier to build experiments with until OpenAPI's official API for ChatGPT is released.

The first time you run ChatGPTAPI.init, Chromium will be opened in non-headless mode so you can log in manually. After the first time, Chromium is launched with a persistent context, so you shouldn't need to keep re-logging in.

Usage

async function example() {
const api = new ChatGPTAPI()

// open chromium and wait until the user has logged in
await api.init({ auth: 'blocking' })

// send a message and wait for a complete response, then parse it as markdown
const response = await api.sendMessage(
  'Write a python version of bubble sort. Do not include example usage.'
)

/* // response
Here is an implementation of bubble sort in Python:

\`\`\`python
def bubble_sort(lst):
  # Set the initial flag to True to start the loop
  swapped = True

  # Keep looping until there are no more swaps
  while swapped:
    # Set the flag to False initially
    swapped = False

    # Loop through the list
    for i in range(len(lst) - 1):
      # If the current element is greater than the next element,
      # swap them and set the flag to True
      if lst[i] > lst[i + 1]:
        lst[i], lst[i + 1] = lst[i + 1], lst[i]
        swapped = True

  # Return the sorted list
  return lst
\`\`\`
*/

Here's the same response rendered as markdown:

Here is an implementation of bubble sort in Python:

def bubble_sort(lst):
  # Set the initial flag to True to start the loop
  swapped = True

  # Keep looping until there are no more swaps
  while swapped:
    # Set the flag to False initially
    swapped = False

    # Loop through the list
    for i in range(len(lst) - 1):
      # If the current element is greater than the next element,
      # swap them and set the flag to True
      if lst[i] > lst[i + 1]:
        lst[i], lst[i + 1] = lst[i + 1], lst[i]
        swapped = True

  # Return the sorted list
  return lst

Note that the default functionality is to parse ChatGPT responses as markdown using html-to-md. I've found the markdown quality to be excellent in my testing, but if you'd rather output plaintext, just pass { markdown: false } to the ChatGPTAPI constructor.

Docs

See the auto-generated docs.

Todo

• Add message and conversation IDs
• Add support for streaming responses

Related

• Inspired by the Go module by Daniel Gross

License

MIT © Travis Fischer

Support my open source work by following me on twitter