Reverse Engineered ChatGPT API by OpenAI. Extensible for chatbots etc.
Status: Working but unmaintained.
python -m pip install --upgrade revChatGPT
- Minimum - Python3.9
- Recommend - Python3.11+
V1 uses a cloudflare bypass proxy to make life convenient for everyone. The proxy is open source: https://github.com/acheong08/ChatGPT-Proxy-V4
To set your own deployed proxy, set the environment variable CHATGPT_BASE_URL
to https://yourproxy.com/api/
CHATGPT_BASE_URL
to https://yourproxy.com/api/
- Proxy server: 5 requests / 10 seconds
- OpenAI: 50 requests / hour for each account
- Create account on OpenAI's ChatGPT
- Save your email and password
Currently broken for free users. Do
export PUID="..."
if you have a plus account. The PUID is a cookie named_puid
Not supported for Google/Microsoft accounts.
{
"email": "email",
"password": "your password"
}
Please this! https://chat.openai.com/api/auth/session
{
"access_token": "<access_token>"
}
{
"conversation_id": "UUID...",
"parent_id": "UUID...",
"proxy": "...",
"model": "gpt-4", // gpt-4-browsing, text-davinci-002-render-sha, gpt-4, gpt-4-plugins
"plugin_ids" : ["plugin-d1d6eb04-3375-40aa-940a-c2fc57ce0f51"] // Wolfram Alpha example
}
- Save this as
$HOME/.config/revChatGPT/config.json
- If you are using Windows, you will need to create an environment variable named
HOME
and set it to your home profile for the script to be able to locate the config.json file.
Plugin IDs can be found here. Remember to set model to gpt-4-plugins
if plugins are enabled. Plugins may or may not work if you haven't installed them from the web interface. You can call chatbot.install_plugin(plugin_id=plugin_id)
to install any one of them from code. Call chatbot.get_plugins()
to get a list of all plugins available.
python3 -m revChatGPT.V1
ChatGPT - A command-line interface to OpenAI's ChatGPT (https://chat.openai.com/chat)
Repo: github.com/acheong08/ChatGPT
Type '!help' to show a full list of commands
Logging in...
You:
(Press Esc followed by Enter to finish)
The command line interface supports multi-line inputs and allows navigation using arrow keys. Besides, you can also edit history inputs by arrow keys when the prompt is empty. It also completes your input if it finds matched previous prompts. To finish input, press Esc
and then Enter
as solely Enter
itself is used for creating new line in multi-line mode.
Set the environment variable NO_COLOR
to true
to disable color output.
from revChatGPT.V1 import Chatbot
chatbot = Chatbot(config={
"access_token": "<your access_token>"
})
print("Chatbot: ")
prev_text = ""
for data in chatbot.ask(
"Hello world",
):
message = data["message"][len(prev_text) :]
print(message, end="", flush=True)
prev_text = data["message"]
print()
from revChatGPT.V1 import Chatbot
chatbot = Chatbot(config={
"access_token": "<your access_token>"
})
prompt = "how many beaches does portugal have?"
response = ""
for data in chatbot.ask(
prompt
):
response = data["message"]
print(response)
Refer to the wiki for advanced developer usage.
Recently released by OpenAI
- Paid
Recently released by OpenAI
- Paid
Get API key from https://platform.openai.com/account/api-keys
python3 -m revChatGPT.V3 --api_key <api_key>
$ python3 -m revChatGPT.V3 --help
ChatGPT - Official ChatGPT API
Repo: github.com/acheong08/ChatGPT
Type '!help' to show a full list of commands
Press Esc followed by Enter or Alt+Enter to send a message.
usage: V3.py [-h] --api_key API_KEY [--temperature TEMPERATURE] [--no_stream] [--base_prompt BASE_PROMPT]
[--proxy PROXY] [--top_p TOP_P] [--reply_count REPLY_COUNT] [--enable_internet]
[--config CONFIG] [--submit_key SUBMIT_KEY] [--model {gpt-3.5-turbo,gpt-4,gpt-4-32k}]
[--truncate_limit TRUNCATE_LIMIT]
options:
-h, --help show this help message and exit
--api_key API_KEY OpenAI API key
--temperature TEMPERATURE
Temperature for response
--no_stream Disable streaming
--base_prompt BASE_PROMPT
Base prompt for chatbot
--proxy PROXY Proxy address
--top_p TOP_P Top p for response
--reply_count REPLY_COUNT
Number of replies for each prompt
--enable_internet Allow ChatGPT to search the internet
--config CONFIG Path to V3 config json file
--submit_key SUBMIT_KEY
Custom submit key for chatbot. For more information on keys, see README
--model {gpt-3.5-turbo,gpt-4,gpt-4-32k}
--truncate_limit TRUNCATE_LIMIT
from revChatGPT.V3 import Chatbot
chatbot = Chatbot(api_key="<api_key>")
chatbot.ask("Hello world")
from revChatGPT.V3 import Chatbot
chatbot = Chatbot(api_key="<api_key>")
for data in chatbot.ask_stream("Hello world"):
print(data, end="", flush=True)
If you have a cool project you want added to the list, open an issue.
This is not an official OpenAI product. This is a personal project and is not affiliated with OpenAI in any way. Don't sue me.
This project exists thanks to all the people who contribute.
- Coding while listening to this amazing song by virtualharby