cd backend
pip install -r requirements.txtpip install pyttsx3 speechrecognition
# For PyAudio on Windows:
pip install pipwin
pipwin install pyaudio# Best for your RTX 4050
ollama pull llama3:8b-instruct-q6_K
# Optional: For complex tasks
ollama pull mixtral:8x7b-instruct-v0.1-q4_K_Mpython -m app.main✅ API running at: http://127.0.0.1:8000 ✅ Docs: http://127.0.0.1:8000/docs
- ✅ Voice interface with emotion
- ✅ Proactive assistant
- ✅ Real-time code execution
- ✅ Self-improvement
- ✅ Multi-language code generation
- ✅ Creative thinking
- ✅ Adaptive memory
POST /query- Main queryGET /health- Health checkGET /features- List features
GET /voice/capabilities- Check voicePOST /voice/speak- Make Ananta speakGET /voice/listen- Listen to user
GET /proactive/checkin- Get check-inPOST /proactive/reminder- Add reminderPOST /proactive/work/start- Start session
POST /code/execute- Run codePOST /code/generate- Generate codePOST /code/test- Test code
GET /memory/stats- StatisticsGET /memory/personal- Personal memoryGET /memory/knowledge- Knowledge
Edit app/config.py:
# Change model
DEFAULT_MODEL = "llama3:8b-instruct-q6_K"
# Adjust personality
DEFAULT_PERSONALITY_LEVEL = 7 # 1-10
# Voice settings
VOICE_ENABLED = True
VOICE_RATE = 175
# Proactive settings
CHECKIN_FREQUENCY = 180 # minutes# Health check
curl http://127.0.0.1:8000/health
# Query
curl -X POST http://127.0.0.1:8000/query \
-H "Content-Type: application/json" \
-d '{"text":"Hello Ananta!"}'
# Voice capabilities
curl http://127.0.0.1:8000/voice/capabilitiesPyAudio won't install?
pip install pipwin
pipwin install pyaudioVoice not working?
- Check microphone permissions
- Test:
python -c "import speech_recognition"
Model not found?
ollama pull llama3:8b-instruct-q6_Kbackend/
├── app/ # API layer
├── core/ # Core functionality
├── engines/ # AI engines
├── memory/ # Memory systems
├── intelligence/ # Self-improvement
├── features/ # Voice, proactive, executor
├── utils/ # Utilities
└── data/ # Storage
Ready! 🎉