Metadata-Version: 2.4
Name: freeai-utils
Version: 0.4.3
Summary: A free, zero-config AI utility toolkit with voice, text, image, and web integrations, pdf_docx readability
Author-email: truongbaan <truongbaansoftware@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/truongbaan/Utility-python-library
Requires-Python: >=3.9.13
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pyaudio
Requires-Dist: numpy
Requires-Dist: keyboard
Requires-Dist: lameenc
Requires-Dist: openai-whisper
Requires-Dist: librosa
Requires-Dist: torch
Requires-Dist: google-genai
Requires-Dist: pyperclip
Requires-Dist: python-dotenv
Requires-Dist: googlesearch-python
Requires-Dist: requests
Requires-Dist: beautifulsoup4
Requires-Dist: readability-lxml
Requires-Dist: transformers
Requires-Dist: Pillow
Requires-Dist: pyautogui
Requires-Dist: easyocr
Requires-Dist: gTTS
Requires-Dist: playsound==1.2.2
Requires-Dist: pyttsx3
Requires-Dist: pymupdf
Requires-Dist: pypdf
Requires-Dist: pdfplumber
Requires-Dist: python-docx
Requires-Dist: mutagen
Requires-Dist: haystack-ai
Requires-Dist: langdetect
Requires-Dist: translators
Requires-Dist: ffmpeg-python
Requires-Dist: imageio-ffmpeg
Requires-Dist: accelerate
Requires-Dist: sentencepiece
Requires-Dist: tiktoken
Requires-Dist: click
Requires-Dist: hf_xet
Dynamic: license-file

# freeai-utils

A lightweight, pip‑installable Python toolkit that wraps popular AI and utility libraries into classes and functions (no external binaries or convoluted setup scripts required). 

Most selected models fall in the **81–242 million parameter** range, which pioritizes real time responsiveness while still delivering solid accuracy. Instead of writing long pipelines or dealing with low level APIs, you get smart defaults out of the box, with the option to customize behavior at init time if needed. 

The first time you use a feature that needs a model (like image captioning or Whisper), it will automatically download the model from Hugging Face. After that, it will work offline using the cached version.

**Note**: This library focuses on being simple to use, even if it means sacrificing accuracy. It's great for beginners or anyone who wants to explore AI features without dealing with complex code. Just call the functions, I'll handle the rest.

## Features

- **Audio**: record WAV/MP3 (fixed, toggle, silence-triggered)  
- **Speech-to-Text**: OpenAI Whisper transcription & language detection   
- **Web Search**: scrape Google results  
- **Image**: caption generation & OCR (EasyOCR)  
- **TTS**: text-to-speech via gTTS or pyttsx3
- **PDF-DOCX-Reader**: extract text and images from pdf and docx files
- **Document Filter**: extract and rank relevant content from documents using an extractive QA model (TinyRoBERTa by default)
- **Translator**: Provides automatic language detection, translating content into your specified target language. (both online and local)
- **LocalLLM**: Small Qwen model for offline use or as a chatbot without an API key.
- **ImageGenerator**: Easy interaction with SDXL Turbo and SD1.5 models for image generation (for UI and performance, consider using AUTOMATIC1111) (Not done)
* **Gemini API**: Interact with Google Cloud Gemini models via your API key

  * *Note: This works best with Google accounts that have no billing method added yet (completely free to use with limits).*

## Installation

```bash
pip install freeai-utils
```

> No need to install extra executables or clone large repositories — everything works out of the box with `pip`.

---

## Models download 
```bash
freeai-utils setup
```
or
```bash
freeai-utils setup A
```

>This will help downloads default models for most functional classes (excluding image generation).

For image generation models:
```bash
freeai-utils setup ICF
```

For more detailed control over which models to download:
```bash
freeai-utils guide
```
>This will displays a list of setup options for specific model types. You can also trigger downloads programmatically by instantiating the relevant class.

## 📖 Full API Reference

For a detailed list of all classes and methods, see [API.md](https://github.com/truongbaan/Utility-python-library/blob/main/API.md).

## Acknowledgements & References

See [THIRD_PARTY.md](https://github.com/truongbaan/Utility-python-library/blob/main/THIRD_PARTY.md) for a full list of third-party libraries and their licenses.

## Inspiration

This project was inspired by the GitHub repository:
[awesome-python](https://github.com/vinta/awesome-python)

## License
This project is licensed under the MIT License - see the [LICENSE](https://github.com/truongbaan/Utility-python-library/blob/main/LICENSE) file for details.
