The reverse engineering the chat feature of the new version of Bing
python3 -m pip install EdgeGPT --upgrade- 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)
!!! 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.
- 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.
- Open bing.com/chat
- If you see a chat feature, you are good to continue...
- Install the cookie editor extension for Chrome or Firefox
- Go to bing.com
- Open the extension
- Click "Export" on the bottom right, then "Export as JSON" (This saves your cookies to clipboard)
- 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
- NOTE: The cookies file name MUST follow the regex pattern
cookies = json.loads(open("./path/to/cookies.json", encoding="utf-8").read()) # might omit cookies option
bot = await Chatbot.create(cookies=cookies) $ 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)
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())Create a simple Bing Chat AI query (using the 'precise' conversation style by default) and see just the main text output rather than the whole API response:
Remember to store your cookies in a specific format: bing_cookies_*.json.
from EdgeGPT.EdgeUtils import Query, Cookie
q = Query("What are you? Give your answer as Python code")
print(q)Or change the conversation style or cookie file to be used:
q = Query(
"What are you? Give your answer as Python code",
style="creative", # or: 'balanced', 'precise'
cookie_file="./bing_cookies_alternative.json"
)Quickly extract the text output, code snippets, list of sources/references, or suggested follow-on questions using the following attributes:
q.output
q.code
q.suggestions
q.sources # for the full json output
q.sources_dict # for a dictionary of titles and urlsGet the original 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 fileAnd 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 try using the next file (alphabetically) if you've exceeded your daily quota of requests (currently set at 200).
Here are the main attributes which you can access:
Cookie.current_file_index
Cookie.dirpath
Cookie.search_pattern # default is `bing_cookies_*.json`
Cookie.files() # list as files that match .search_pattern
Cookie.current_filepath
Cookie.current_data
Cookie.import_next()
Cookie.image_token
Cookie.ignore_filesThis 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/edgegptYou can add any extra flags as following
docker run --rm -it -v $(pwd)/cookies.json:/cookies.json:ro -e COOKIE_FILE='/cookies.json' ghcr.io/acheong08/edgegpt --rich --style creative$ 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 asyncioGenerate 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")
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))