Setup Protocol: INITIATED
Complete each task in sequence. Tasks unlock automatically as you progress.
GPU Selection
Verify your NVIDIA GPU meets minimum requirements for local LLM hosting.
Requirements:
- Minimum: RTX 4070 (12GB VRAM)
- Recommended: RTX 4090 (24GB VRAM)
- Enterprise: A6000/A100 (48GB VRAM)
Verify Installation:
nvidia-smi
Driver version 535+ recommended for CUDA 12 compatibility.
Docker & Compose
Install Docker and Docker Compose for container management.
Windows Installation:
# Download Docker Desktop from # https://www.docker.com/products/docker-desktop/ # Verify installation docker --version docker-compose --version
Linux Installation:
curl -fsSL https://get.docker.com -o get-docker.sh sudo sh get-docker.sh sudo usermod -aG docker $USER
Windows: Enable WSL2 backend for best performance.
Ollama Service
Setup Ollama for local LLM model management and API access.
Installation:
# Download from https://ollama.ai # Verify installation ollama --version # Pull recommended models ollama pull llama3.2 ollama pull mistral ollama pull nomic-embed-text
Start Service:
ollama serve
Ollama runs on port 11434 by default.
Vector Store
Install ChromaDB for semantic search and RAG capabilities.
Installation:
pip install chromadb>=0.4.0
Verify:
python -c "import chromadb; print(chromadb.__version__)"
ChromaDB creates a local directory for persistent storage.
Python Environment
Setup Python 3.9+ and install all required dependencies.
Install Dependencies:
pip install -r requirements.txt
Verify Python Version:
python --version
Python 3.9 or higher required.
FastAPI Backend
Configure and launch the AI-Radar application backend.
Environment Configuration:
OLLAMA_BASE_URL=http://localhost:11434 LLM_MODEL=llama3.2 EMBEDDING_MODEL=nomic-embed-text CHROMA_PERSIST_DIR=./chroma_store DATABASE_URL=sqlite:///./ai_radar.db
Start Application:
# Development uvicorn app.main:app --reload --host 0.0.0.0 --port 8000 # Production (Docker) docker-compose up -d
SUCCESS: Access at http://localhost:8000
> ADVANCED_GUIDES
Deep-dive documentation for complex scenarios, optimization, and production deployments.
> NO_GUIDES_FOUND
No advanced guides available yet. Complete the setup wizard above to get started.