System requirements
AI Smart Redact ships as Docker images and supports Docker Compose and Kubernetes deployments. Plan resource allocation per service container before bringing up the stack.
Service architecture
AI Smart Redact runs as three cooperating subsystems. Integrating systems call the Manager directly for API workflows, or go through the Orchestrator for browser-based review. The Manager dispatches detection and redaction work to the Worker, which runs the AI model and the rules engine.
For databases, file storage, ports, and protocols, refer to Architecture.
Per-service allocation
The following table lists the minimum RAM and CPU allocation per service container, with notes on what drives each figure:
| Service | RAM | CPU | Notes |
|---|---|---|---|
| Worker (CPU) | 4 GB | 2 cores | The AI model loads ~2.9 GB into memory at startup. Detection pins one core at 100%. |
| Worker (GPU) | 4 GB+ | 2 cores | GPU inference offloads compute, but the model still loads into RAM. VRAM requirements depend on the GPU. |
| Manager | 1 GB | 2 cores | Baseline ~217 MB. Peaks during file encryption at about two times the file size per concurrent upload. |
| Orchestrator | 1 GB | 2 cores | Similar profile to Manager (proxies uploads, manages sessions). |
| PostgreSQL (per DB) | 512 MB | 1 core | Observed 44-73 MB under load. 512 MB provides headroom for query cache and connection state. |
| RabbitMQ | 512 MB | 1 core | Lightweight for this workload. Increase if queue depths grow large (>10k messages). |
| Redis | 256 MB | 0.5 core | Ephemeral session/token cache only (no persistence). |
Total minimum for the full stack (CPU mode): ~8.5 GB RAM, 9.5 CPU cores. This includes two PostgreSQL instances: one for the Manager and one for the Orchestrator.
GPU acceleration
A CUDA-compatible GPU is optional but recommended for higher detection throughput at scale. The Worker still loads the AI model into RAM, so the Worker (GPU) row replaces, rather than adds to, the CPU Worker allocation when you run the GPU variant.
For GPU setup and scaling guidance, refer to Scale AI Smart Redact and Worker configuration.
Containerization
AI Smart Redact is distributed as Docker images. For deployment with Docker Compose, refer to Get started with AI Smart Redact. For Kubernetes, refer to Configure AI Smart Redact.