Skip to content

Reverse engineered API of Microsoft's Bing Chat AI

License

Notifications You must be signed in to change notification settings

markus-nclose/EdgeGPT

 
 

Repository files navigation

EdgeGPT

Edge GPT

The reverse engineering the chat feature of the new version of Bing

English - 简体中文 - 繁體中文 - Español - 日本語

PyPI version Python version Total downloads

Setup

Install package

python3 -m pip install EdgeGPT --upgrade

Requirements

  • python 3.8+
  • A Microsoft Account with access to https://bing.com/chat (Optional, depending on your region)
  • Required in a supported country or region with New Bing (Chinese mainland VPN required)
  • Selenium (for automatic cookie setup)

Authentication

!!! POSSIBLY NOT REQUIRED ANYMORE !!!

In some regions, Microsoft has made the chat feature available to everyone, so you might be able to skip this step. You can check this with a browser (with user-agent set to reflect Edge), by trying to start a chat without logging in.

It was also found that it might depend on your IP address. For example, if you try to access the chat features from an IP that is known to belong to a datacenter range (vServers, root servers, VPN, common proxies, ...), you might be required to log in while being able to access the features just fine from your home IP address.

If you receive the following error, you can try providing a cookie and see if it works then:

Exception: Authentication failed. You have not been accepted into the beta.

Collect cookies

  1. Get a browser that looks like Microsoft Edge.
  • a) (Easy) Install the latest version of Microsoft Edge
  • b) (Advanced) Alternatively, you can use any browser and set the user-agent to look like you're using Edge (e.g., Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.51). You can do this easily with an extension like "User-Agent Switcher and Manager" for Chrome and Firefox.
  1. Open bing.com/chat
  2. If you see a chat feature, you are good to continue...
  3. Install the cookie editor extension for Chrome or Firefox
  4. Go to bing.com
  5. Open the extension
  6. Click "Export" on the bottom right, then "Export as JSON" (This saves your cookies to clipboard)
  7. Paste your cookies into a file bing_cookies_*.json.
    • NOTE: The cookies file name MUST follow the regex pattern bing_cookies_*.json, so that they could be recognized by internal cookie processing mechanisms

Use cookies in code:

cookies = json.loads(open("./path/to/cookies.json", encoding="utf-8").read())  # might omit cookies option
bot = await Chatbot.create(cookies=cookies)

How to use Chatbot

Run from Command Line

 $ python3 -m EdgeGPT.EdgeGPT -h

        EdgeGPT - A demo of reverse engineering the Bing GPT chatbot
        Repo: github.com/acheong08/EdgeGPT
        By: Antonio Cheong

        !help for help

        Type !exit to exit

usage: EdgeGPT.py [-h] [--enter-once] [--search-result] [--no-stream] [--rich] [--proxy PROXY] [--wss-link WSS_LINK]
                  [--style {creative,balanced,precise}] [--prompt PROMPT] [--cookie-file COOKIE_FILE]
                  [--history-file HISTORY_FILE] [--locale LOCALE]

options:
  -h, --help            show this help message and exit
  --enter-once
  --search-result
  --no-stream
  --rich
  --proxy PROXY         Proxy URL (e.g. socks5://127.0.0.1:1080)
  --wss-link WSS_LINK   WSS URL(e.g. wss://sydney.bing.com/sydney/ChatHub)
  --style {creative,balanced,precise}
  --prompt PROMPT       prompt to start with
  --cookie-file COOKIE_FILE
                        path to cookie file
  --history-file HISTORY_FILE
                        path to history file
  --locale LOCALE       your locale (e.g. en-US, zh-CN, en-IE, en-GB)

(China/US/UK/Norway has enhanced support for locale)

Run in Python

1. The Chatbot class and asyncio for more granular control

Use Async for the best experience, for example:

import asyncio, json
from EdgeGPT.EdgeGPT import Chatbot, ConversationStyle

async def main():
    bot = await Chatbot.create() # Passing cookies is "optional", as explained above
    response = await bot.ask(prompt="Hello world", conversation_style=ConversationStyle.creative, simplify_response=True)
    print(json.dumps(response, indent=2)) # Returns
    """
    {
        "text": str
        "author": str
        "sources": list[dict]
        "sources_text": str
        "suggestions": list[str]
        "messages_left": int
    }
    """
    await bot.close()

if __name__ == "__main__":
    asyncio.run(main())

2) The Query, ImageQuery, and Cookie helper classes

First store your cookies in the default folder HOME/bing_cookies using the naming standard: bing_cookies_*.json, then it's super easy to create a Bing Chat query (in the 'precise' conversation style by default) and use the many helper method to get straight to the information you want, rather than writing more boiler-plate code to parse the API response:

from EdgeUtils import Query, ImageQuery, Cookie
  
q = Query("What are you? Give your answer as Python code")
print(q)

To change the location or naming convention of cookie files manually, just update these Cookie attributes before creating your Query/ImageQuery:

Cookie.search_pattern = "account_*.json"
Cookie.dir_path = Path.home() / "my_private_cookies"

To change the conversation style:

q = Query(
  "What are you? Give your answer as Python code",
  style="creative",  # or 'balanced' or 'precise' (default)
)

Quickly extract the text output, code snippets, list of sources/references, or suggested follow-on questions using the following attributes:

q.output
q.code_blocks
q.suggestions
q.sources       # for the full json output
q.sources_dict  # for a dictionary of titles and urls

Get the orginal prompt and the conversation style you specified:

q.prompt
q.style
repr(q)

Access previous Queries made since importing Query:

Query.index  # A list of Query objects; updated dynamically
Query.request_count  # A tally of requests made using each cookie file

And finally, the Cookie class supports multiple cookie files, so if you create additional cookie files with the naming convention bing_cookies_*.json, your queries will automatically cycle through to the next file (alphabetically) and add them to Cookie.ignore_files once you've exceeded your daily quota of requests (currently 200).

Here are some of the attributes you can access:

Cookie.rotate_cookies
Cookie.supplied_files
Cookie.request_count
Cookie.current_file_index
Cookie.dir_path
Cookie.search_pattern  # default is `bing_cookies_*.json`
Cookie.files()  # list as files that match .search_pattern
Cookie.current_file_path
Cookie.current_data
Cookie.import_next()
Cookie.image_token
Cookie.ignore_files

For a full list of methods and attributes, please have a look at EdgeUtils.demo()


Run with Docker

This assumes you have a file cookies.json in your current working directory

docker run --rm -it -v $(pwd)/cookies.json:/cookies.json:ro -e COOKIE_FILE='/cookies.json' ghcr.io/acheong08/edgegpt

You can add any extra flags as following

docker run --rm -it -v $(pwd)/cookies.json:/cookies.json:ro -e COOKIE_FILE='/cookies.json' ghcr.io/acheong08/edgegpt --rich --style creative

How to use Image generator

Run from Command Line

$ python3 -m ImageGen.ImageGen -h
usage: ImageGen.py [-h] [-U U] [--cookie-file COOKIE_FILE] --prompt PROMPT [--output-dir OUTPUT_DIR] [--quiet] [--asyncio]

optional arguments:
  -h, --help            show this help message and exit
  -U U                  Auth cookie from browser
  --cookie-file COOKIE_FILE
                        File containing auth cookie
  --prompt PROMPT       Prompt to generate images for
  --output-dir OUTPUT_DIR
                        Output directory
  --quiet               Disable pipeline messages
  --asyncio             Run ImageGen using asyncio

Run in Python

1) The ImageQuery helper class

Generate images based on a simple prompt and download to the current working directory:

from EdgeGPT.EdgeUtils import ImageQuery

q=ImageQuery("Meerkats at a garden party in Devon")

Change the download directory for all future images in this session:

Query.image_dirpath = Path("./to_another_folder")

2) The ImageGen class and asyncio for more granular control

from EdgeGPT.ImageGen import ImageGen
import argparse
import json

async def async_image_gen(args) -> None:
    async with ImageGenAsync(args.U, args.quiet) as image_generator:
        images = await image_generator.get_images(args.prompt)
        await image_generator.save_images(images, output_dir=args.output_dir)

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("-U", help="Auth cookie from browser", type=str)
    parser.add_argument("--cookie-file", help="File containing auth cookie", type=str)
    parser.add_argument(
        "--prompt",
        help="Prompt to generate images for",
        type=str,
        required=True,
    )
    parser.add_argument(
        "--output-dir",
        help="Output directory",
        type=str,
        default="./output",
    )
    parser.add_argument(
        "--quiet", help="Disable pipeline messages", action="store_true"
    )
    parser.add_argument(
        "--asyncio", help="Run ImageGen using asyncio", action="store_true"
    )
    args = parser.parse_args()
    # Load auth cookie
    with open(args.cookie_file, encoding="utf-8") as file:
        cookie_json = json.load(file)
        for cookie in cookie_json:
            if cookie.get("name") == "_U":
                args.U = cookie.get("value")
                break

    if args.U is None:
        raise Exception("Could not find auth cookie")

    if not args.asyncio:
        # Create image generator
        image_generator = ImageGen(args.U, args.quiet)
        image_generator.save_images(
            image_generator.get_images(args.prompt),
            output_dir=args.output_dir,
        )
    else:
        asyncio.run(async_image_gen(args))

Star History

Star History Chart

Contributors

This project exists thanks to all the people who contribute.

About

Reverse engineered API of Microsoft's Bing Chat AI

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.4%
  • Other 1.6%