Nexa AI: Your AI Assistant

Nexa AI is a sophisticated AI assistant designed to streamline your daily tasks through voice commands. It can open applications, browse websites, manage system settings, and provide intelligent, real-time responses by leveraging advanced AI models.

Features

• Open Apps: Launch any application on your system with a simple voice command.
• Open Websites: Access your favorite websites instantly.
• System Volume Control: Adjust your system's volume (up/down) hands-free.
• Intelligent Responses: Utilizes AI to understand and respond to your queries intelligently.
• Google Search: Performs Google searches and fetches real-time data to answer your questions.
• Image Generation: Generates images using the Hugging Face API based on your descriptions.

Technologies Used

• Backend: Python
• Frontend: PyQt5 (for the GUI)
• APIs & Services: Google Gemini, Hugging Face, Cohere
• Libraries: Selenium, webdriver_manager

Images

Decision-Making Model Diagram

Speech-to-Text Model Diagram for more info checkout my project https://github.com/Aryan-Pardeshi/Speech-To-Text-Selenium

API Keys

To use Nexa AI, you'll need to obtain API keys from the following services:

• Google AI Studio (Gemini Key)
• Hugging Face Tokens
• Cohere API Keys

How It Works

Nexa AI processes voice commands using a speech-to-text engine. The transcribed text is fed into a Decision-Making Model which is like a Brain that categorizes the user's intent into one of three types:

• General Queries: For conversational questions like "How are you?".
• Realtime Queries: For questions requiring real-time information, such as "What's the weather outside?".
• Automation Queries: For commands that perform actions, like "Open Facebook" or "Generate an image."

Based on the category, Nexa either provides a direct response or executes the requested command, converting the output back to speech for a seamless user experience.

Setup Instructions

1. Install Python: Make sure you have Python 3.8 or higher installed.

2. Clone the Repository:

   git clone https://github.com/your-username/Nexa-AI.git
   cd Nexa-AI

3. Create a Virtual Environment (Optional but Recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

4. Install Dependencies:

   pip install -r Requirements.txt

5. Setup .env File: Create a .env file in the root directory and add your API keys in the following format:

   Username = 
   AssistantName = Nexa
   COHERE_API_KEY = 
   HuggingFaceAPIKey=
   GeminiAPIKey = 
   

Credits

This project was created by Aryan Pardeshi.

Acknowledgments

This project utilizes several powerful APIs and libraries. We extend our gratitude to the developers and contributors behind these technologies:

• Web Speech API: For enabling voice recognition and speech synthesis capabilities. More information can be found here.
• Selenium: For browser automation, which is crucial for our web-based interactions. Visit their official site here.
• webdriver_manager: For simplifying the management of browser drivers for Selenium. Check out the project on PyPI.
• Google Gemini: For providing the advanced AI model that powers our intelligent responses. Learn more about Gemini here.
• Cohere: For their powerful language models that enhance our AI's capabilities. Find out more about them here.
• Hugging Face: For their platform and the Qwen/Qwen-Image model, which we use for image generation. Explore the model here.
• PyQt5: For creating the graphical user interface. More information can be found here.