aionui 1.4.2

A powerful Python library for automating interactions with AI models (ChatGPT, Claude, Gemini) through their web interfaces using Playwright. Supports both synchronous and asynchronous operations, file handling, and multi-platform compatibility.

AI On UI (aionui)

A powerful Python library for automating interactions with AI models (ChatGPT, Claude, Gemini) through their web interfaces. Supports both synchronous and asynchronous operations, file handling, and cross-platform compatibility.

Key Features

• 🤖 Multiple AI Model Support:

  • ChatGPT
  • Claude
  • Gemini

• 🔄 Dual Operation Modes:

  • Sync: for sequential code
  • Async: for asynchronous applications

• 📦 Versatile Data Handling:

  • Text responses
  • Code blocks
  • JSON structures
  • Images
  • File upload/download

• 🛠 Advanced Features:

  • Web search (ChatGPT)
  • Large file processing
  • Retry mechanism
  • Detailed logging
  • Cross-platform support

Installation

pip install aionui

Requirements

• Python 3.10+
• Google Chrome
• Playwright

Quickstart

Synchronous Usage

from aionui import AiOnUi

# Initialize
aionui = AiOnUi()

# ChatGPT
with aionui.model_sync("gpt") as model:
    response = model.chat("Hello!")
    print(response)

# Claude
with aionui.model_sync("claude") as model:
    response = model.chat("Hello!")
    print(response)

# Gemini
with aionui.model_sync("gemini") as model:
    response = model.chat("Hello!")
    print(response)

Asynchronous Usage

import asyncio
from aionui import AiOnUi

async def main():
    aionui = AiOnUi()
    
    async with aionui.model_async("gpt") as model:
        response = await model.chat("Hello!")
        print(response)

# Run
asyncio.run(main())

Configuration

Create a config.yaml file:

# Chrome settings
chrome_binary_path: "/usr/bin/google-chrome"  # Path to Chrome binary
user_data_dir: "~/chrome-data"                # Profile directory
debug_port: 9222                              # Port to connect over devtools protocol

Use the config:

aionui = AiOnUi("config.yaml")

Advanced Examples

File Upload and Analysis

async with aionui.model_async("claude") as model:
    # Upload file
    await model.text_as_file("Content for analysis", "data.txt")
    
    # Analyze
    response = await model.chat("Analyze the uploaded data")
    print(response)

Web Search with ChatGPT

with aionui.model_sync("gpt") as model:
    response = model.chat(
        "Latest news about AI?",
        tools=["search_the_web"]
    )
    print(response)

JSON Response

with aionui.model_sync("gemini") as model:
    json_response = model.chat(
        "List 3 programming languages",
        expected_result="json"
    )
    print(json_response)

Documentation

See more examples and detailed guides in the examples directory.

Contributing

Contributions are welcome! See CONTRIBUTING.md for more details.

License

MIT License - see LICENSE for details.

Credits

Copyright (c) 2024 Vu Tri Anh Hoang - GitHub