My-Assistant is a virtual assistant designed to provide real-time information to users based on voice and image inputs. Leveraging state-of-the-art technologies, My-Assistant can understand user queries and respond accurately and promptly.
- Voice Recognition: Utilizes Deepgram's advanced voice recognition capabilities to accurately capture and interpret user queries.
- Image Processing: Processes images to understand context and provide relevant information.
- Real-Time Responses: Delivers information to users in real-time, ensuring quick and efficient interactions.
- Deepgram: For voice recognition and processing.
- OpenAI: For natural language understanding and generating responses.
- Install Node.js and Next.js -> Frontend
- Install Python -> Backend
- Obtain API keys for Deepgram and OpenAI
-
Clone the repository:
git clone https://github.com/your-username/my-assistant.git
-
Install dependencies:
cd my-assistant/frontend npm install
-
Install dependencies:
cd my-assistant/backend pip install
-
Set up environment variables in backend folder: Create a
.env
file in the root directory and add your API keys:DEEPGRAM_API_KEY=your_deepgram_api_key OPENAI_API_KEY=your_openai_api_key
-
Start the frontend application:
npm start dev
-
Start the backend application:
uvicorn main:app --reload
-
Interact with My-Assistant opening the browser:
- Enable or give permission to microphone & camera
- Click "start recording"
- Deepgram for their voice recognition technology.
- OpenAI for their powerful natural language processing capabilities.
For any questions or suggestions, please contact josepaulct@gmail.com.
Happy assisting! 🚀