Skip to main content

Python client sdk to access GPT's AI-powered conversational functionality (without OpenAI API key nor VPN)

Project description

gpt-api-python

Python client sdk to access GPT's AI-powered conversational functionality (without OpenAI API key nor VPN).

PyPi Package Version

Details refer to https://github.com/beenotung/gpt-api

Remarks

The spirit of this library is to enable developers to use the Platform for Open Exploration (Poe) via API. It's designed to empower integration and application development within the terms of service of Poe, which specifically disallow any form of automation that exceeds the set rate limits. Please use this library responsibly and within the provided guidelines.

Features

  • Intuitive API: Make conversation with GPT models via simple and developer-friendly API.

  • Programming Language Agnostic: Designed to work with any programming language. Integrate GPT-powered conversational functionalities into your existing projects with ease.

  • Responsible Usage: Encourages users to respect the guidelines and rate limits set by Poe.

Installation

pip install gpt-api-python

Usage Example

# Import functions from the Python package
from gpt_api import ask
from gpt_api.cli import clear_screen

# ask GPT a question and wait for complete response
task = ask(question='Can I call GPT API from python?')
file_path = f"task-{task['id']}.html"
with open(file_path, 'w') as file:
	file.write(task['html'])
print(task['text'])


# ask GPT a question and process the partial response in realtime
def show_progress(task):
	clear_screen()
	print(task['question'])
	print('=' * 32)
	print(task['text'])

# Use the chat method
task = gpt.chat(prompt='What can I do with GPT?', callback=show_progress)
print(f"text: {len(task['text'])}, html: {len(task['html'])}")

Detail example can refer to the demo cli.py

Proper Use

It's important to note that Poe's terms of service disallow any form of automation that exceeds the rate limits set forth by Poe. Please ensure to use this library responsibly and within the limits set by Poe. Improper use may lead to suspension of your access to the services.

Potential Use Cases

(This section is generated by GPT-4 itself)

GPT (Generative Pre-trained Transformer) models are powerful language models capable of generating human-like text. They can be used to enable a wide range of functionalities:

  • Chatbots and Conversational Agents: GPT models can be used to create chatbots that can carry on human-like conversations. These chatbots can answer questions, provide recommendations, and even have friendly chats with users.

  • Text Generation and Completion: Given a prompt, GPT models can generate coherent and contextually relevant text. This can be used for tasks such as writing essays, generating code, creating poetry, and much more.

  • Translation: While not specifically trained for translation, GPT models have shown reasonable performance in translating text between languages.

  • Summarization: GPT models can be used to summarize long pieces of text, providing a condensed version while preserving the original meaning.

  • Question Answering: Given a context and a question, GPT models can provide accurate answers, making them useful for tasks like customer support, tutoring, and knowledge extraction.

  • Sentiment Analysis: While not a primary use case, GPT models can be used to analyze the sentiment of a piece of text, identifying whether the sentiment is positive, negative, or neutral.

  • Content Moderation: GPT models can help moderate content, identifying inappropriate or offensive text.

  • Personal Assistants: GPT models can be used to create personal assistants that can schedule appointments, send messages, set reminders, and more.

  • Tutoring: GPT can provide detailed explanations on a wide range of topics, making it a useful tool for education and tutoring.

These applications can be integrated into various software applications, websites, and services to provide a more interactive and personalized user experience.

However, it's important to note that while GPT models are powerful, they are not perfect. They can sometimes generate incorrect or inappropriate responses, and should not be relied upon for critical decision-making without human supervision.

License

This project is licensed with BSD-2-Clause

This is free, libre, and open-source software. It comes down to four essential freedoms [ref]:

  • The freedom to run the program as you wish, for any purpose
  • The freedom to study how the program works, and change it so it does your computing as you wish
  • The freedom to redistribute copies so you can help others
  • The freedom to distribute copies of your modified versions to others

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gpt-api-python-1.0.3.tar.gz (6.4 kB view details)

Uploaded Source

Built Distribution

gpt_api_python-1.0.3-py3-none-any.whl (6.8 kB view details)

Uploaded Python 3

File details

Details for the file gpt-api-python-1.0.3.tar.gz.

File metadata

  • Download URL: gpt-api-python-1.0.3.tar.gz
  • Upload date:
  • Size: 6.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.5

File hashes

Hashes for gpt-api-python-1.0.3.tar.gz
Algorithm Hash digest
SHA256 31d236fdecc71a051556a8aadbd01cdcc28bffe7b87776a7b548035ae24aa5d4
MD5 491e59d9637ea4ee6a70ba2ab25671bd
BLAKE2b-256 629c342c889790bb8c86fe1c80bc42941a40b50aebd7aac44b206f991c599d01

See more details on using hashes here.

File details

Details for the file gpt_api_python-1.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for gpt_api_python-1.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 e4f55bf0f98ac5ccdc52c4acc674423129cf36b8bc233f77b7991c58ed19422e
MD5 53edfc927f5851dca28862edc4d89af7
BLAKE2b-256 1246eeaa5d22702f3e101f31669d64c07d4670aef32c2314d5a27478441741a4

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page