Technical SOP for deploying private AI infrastructure on client hardware or isolated tenants.
Prepare the target machine according to the deployment specifications.
curl -fsSL https://tailscale.com/install.sh | sh sudo tailscale up --authkey=tskey-auth-...
Install and configure the model routing proxy.
pip install litellm litellm --config /path/to/config.yaml --port 4000
Deploy Qdrant vector store and Redis cache.
docker run -p 6333:6333 -v $(pwd)/qdrant_storage:/qdrant/storage qdrant/qdrant docker run -p 6379:6379 redis:latest
Install Ollama for local model inference.
curl -fsSL https://ollama.com/install.sh | sh ollama pull llama3.1:70b ollama pull nomic-embed-text
Create configuration file routing to local Ollama.
model_list:
- model_name: ollama/llama3.1:70b
litellm_params:
model: ollama/llama3.1:70b
api_base: http://localhost:11434
- model_name: ollama/nomic-embed-text
litellm_params:
model: ollama/nomic-embed-text
api_base: http://localhost:11434
Verify PII detection and redaction before storage.
python -m oction.deid.test --client-id CLIENT_ID --sample-data /path/to/test/docs
curl http://localhost:4000/health ./oction-node.sh status