Skip to main content

Lightweight version of ChatGPT

Uses API by Pawan

Disclaimer

This is not open source. PawanOsman can see all your requests and your session token.

Install

pip3 install ChatGPT-lite

Setup:

Getting session token

Check https://github.com/acheong08/ChatGPT/wiki/Setup

Usage

Command line

usage: ChatGPT-lite [-h] [--session_token SESSION_TOKEN] [--bypass_node BYPASS_NODE (optional)] [--async_mode]

Example development:

import argparse
import sys
import asyncio
from ChatGPT_lite.ChatGPT import Chatbot


async def async_main(args):
    if args.session_token is None:
        print("Please provide a session token")
        sys.exit(1)

    chat = Chatbot(args.session_token, args.bypass_node)
    await asyncio.gather(chat.wait_for_ready())

    while True:
        try:
            prompt = input("You: ")
            if prompt == "!exit":
                break
            response = await chat.ask(prompt)
            print(f"\nBot: {response['answer']}\n")
        except KeyboardInterrupt:
            break
    # Close sockets
    chat.close()
    # exit
    sys.exit(0)


def sync_main(args):
    chat = Chatbot(args.session_token, args.bypass_node)
    # Create loop
    loop = asyncio.new_event_loop()
    # Set
    asyncio.set_event_loop(loop)
    # Run
    loop.run_until_complete(chat.wait_for_ready())
    while True:
        try:
            prompt = input("You: ")
            if prompt == "!exit":
                break
            response = loop.run_until_complete(chat.ask(prompt))
            print(f"\nBot: {response['answer']}\n")
        except KeyboardInterrupt:
            break
    # Close sockets
    chat.close()
    # stop asyncio event loop
    loop.stop()
    # exit
    sys.exit(0)


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--session_token', type=str, default=None)
    parser.add_argument('--bypass_node', type=str,
                        default="https://gpt.pawan.krd")
    parser.add_argument('--async_mode', action='store_true')
    args = parser.parse_args()

    if args.session_token is None:
        print("Please provide a session token")
        sys.exit(1)

    print("Starting. Please wait...")
    if args.async_mode:
        asyncio.run(async_main(args))
    else:
        sync_main(args)


if __name__ == "__main__":
    main()

Metadata

Release files for ChatGPT-lite 0.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ChatGPT-lite 0.0.5
File Size Uploaded Provenance Actions
ChatGPT_lite-0.0.5.tar.gz 4.7 kB Without provenance Details for ChatGPT_lite-0.0.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ChatGPT-lite 0.0.5
File Interpreter ABI Platform Actions
ChatGPT_lite-0.0.5-py3-none-any.whl Python 3 none any Details for ChatGPT_lite-0.0.5-py3-none-any.whl

Total release size: 10.4 kB

Release files / ChatGPT_lite-0.0.5.tar.gz

Download URL ChatGPT_lite-0.0.5.tar.gz
Size 4.7 kB
Tags Source
SHA-256 checksum
How to use checksums
9ca1701107cc1ef196a280e20d3e1852c02c79055ebae48143690b8084759e84
BLAKE2b-256 checksum
How to use checksums
3386e97dafede302b3397a6108e95c518b8988a656bcc0a1c92d660867b12d6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Release files / ChatGPT_lite-0.0.5-py3-none-any.whl

Download URL ChatGPT_lite-0.0.5-py3-none-any.whl
Size 5.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f1941929bfd8b7bf051f48d6247c89513a0e88749d8af344231b0191c77e432a
BLAKE2b-256 checksum
How to use checksums
93d7e3448c785fecfb82ead7d9ecb380ba7751cb46afbac50b05b3db02bcb9e9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Security for ChatGPT-lite 0.0.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page