AI Sandbox is a comprehensive toolkit that provides various AI-powered features. It's a great place to explore and experiment with AI technologies.
-
Text Completion: Enhance your typing experience with AI-powered text completion. It predicts and suggests the next piece of text as you type.
-
Streaming Support: Real-time data streaming is supported, allowing for dynamic and interactive user experiences.
-
Audio Input: The application can take audio input, opening up possibilities for voice-activated commands or audio analysis.
- OpenAI GPT: Requires API key from OpenAI
- Google Gemini: Requires API key from Google AI Studio
- Llama 3.2: Runs locally through Ollama
- DeepSeek-r1: Runs locally through Ollama
-
API Keys Setup:
- Get OpenAI API key from OpenAI Platform
- Get Google API key from Google AI Studio
-
Ollama Setup (for Llama and DeepSeek):
- Install Ollama from ollama.ai
- Pull the models:
ollama pull llama3.2 ollama pull deepseek-r1:8b
- Start Ollama service locally
Backend Setup:
# Navigate to backend directory
cd backend
# Copy environment file and update with your API keys
cp .env.example .env
# Install dependencies
npm install
# Start the server
npm startFrontend Setup:
# Navigate to frontend directory
cd app
# Install dependencies
npm install
# Start the server
npm start# Build and start all services
docker-compose up --build- Frontend: http://localhost:3000
- Backend API: http://localhost:5001
Update the .env file in the backend directory with your API keys:
OPENAI_API_KEY=your_openai_key_here
GOOGLE_API_KEY=your_google_key_here
- OpenAI and Google Gemini services require valid API keys in the .env file
- Llama and DeepSeek services require Ollama to be running locally on port 11434
- The application allows switching between different AI models through the interface
Enjoy exploring the AI Sandbox