Ethiopian Data Residency, On-Premise Inference, and Sovereignty

1. Overview & Technical Architecture#

Government ministries, financial institutions, and defense enterprises require strict in-country data residency where no sensitive information leaves the physical server room.

1. Air-Gapped Deployment Architecture#

SmartERP's sovereign inference engine can run entirely within an isolated local area network (LAN) with zero external internet connectivity:

[Local Workstations] ──> [SmartERP Monorepo (LAN)] ──> [Inference Server (LAN / GPU)]
                                                             └── Model Weights on NVMe

All model weights, tokenizer vocabularies, and vector embeddings reside on local encrypted NVMe storage.

2. Prerequisites & Infrastructure Requirements#

• Runtime Environment: Python 3.12+, PostgreSQL 16 with pgvector extension.
• Security Access Group: Ashewa AI / Administrator (Technical ID: muk_ai.group_ai_manager)
• Hardware Profile: Minimum 16 GB System RAM (CPU inference) or NVIDIA GPU with 8+ GB VRAM.

3. Step-by-Step Configuration & Verification#

Step 1: Navigating to Model Management#

1. Access your SmartERP instance at https://smarterp.et/odoo.
2. Open Settings → Technical → Ashewa AI → Model Registry.
3. Select the custom model profile.

{screenshot:60-localized-data-residency-and-sovereignty-step1-navigation}

Step 2: Testing Endpoint Health & Response Verification#

1. Click the Run Diagnostic Health Check button.
2. Verify token generation speed (tokens/sec) and latency benchmarks.
3. Review sample response in the diagnostic console.

{screenshot:60-localized-data-residency-and-sovereignty-step2-verification}

4. Advanced Configuration Points#

• Automated Tasks: muk_ai.ir_cron_model_health_monitor runs every 15 minutes.
• Multi-Tenant Boundaries: Custom model fine-tuning adapters are strictly segregated per tenant database.

5. Comprehensive Troubleshooting Matrix#