A simple REST API powered by AI that generates text responses. Perfect for chatbots, content generation, and AI-powered applications.

• Docker installed on your system
• At least 4GB free RAM

git clone https://github.com/Anandesh-Sharma/minivault-api.git
cd minivault-api
./setup.sh

That's it! The API will be running at http://localhost:8000

Send a POST request to generate AI responses:

curl -X POST http://localhost:8000/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Write a short poem about the ocean"}'

For real-time streaming responses:

curl -X POST http://localhost:8000/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Tell me a story", "stream": true}'

curl http://localhost:8000/health

{
  "prompt": "Your question or instruction here",
  "stream": false
}

• prompt: Your text input (required)
• stream: Set to true for real-time streaming (optional)

{
  "response": "AI generated text response",
  "model": "minivault-ollama",
  "response_time_ms": 1250
}

# Check container status
docker ps

# Restart everything
docker-compose down
./setup.sh

# API logs
docker logs minivault-api

# Ollama logs  
docker logs minivault-ollama

• Chatbots: Real-time conversational AI
• Content Generation: Articles, blogs, product descriptions
• Code Assistance: Programming help and code generation
• Creative Writing: Stories, poems, creative content
• Summarization: Text summary and analysis
• Q&A Systems: Automated question answering

• API Documentation: http://localhost:8000/docs (when running)
• Health Check: http://localhost:8000/health
• Logs: Check logs/log.jsonl for interaction history

• Model: tinyllama:latest (lightweight, fast)
• Response Time: ~1-3 seconds typical
• Memory Usage: ~2-4GB RAM
• Streaming: Real-time token-by-token output
• CPU Only: No GPU required

Ready to start generating AI content? Run ./setup.sh and you're good to go! 🚀