Documentation

GENIE.AI architecture, deployment, and integration guides.

GENIE.AI Documentation

Sovereign, DPG-compliant generative AI / RAG framework for the public sector. Multilingual retrieval-augmented generation, integrated with OPEA (Open Platform for Enterprise AI), built for government and public-sector deployments.

Start here

New to GENIE.AI? Read in this order:

  1. Project Overview — what GENIE.AI is and why it exists
  2. Development Guide — set up a local dev environment
  3. Docker Compose Setup — single-node deployment
  4. Architecture Overview — C4 container view of the system

Sections

Guides vs. Reference

  • Guides walk through a task end-to-end (e.g. Docker Compose Setup, Development Guide).
  • Reference describes the system as it exists (e.g. Architecture Overview, API Contracts, UI Component Inventories).

Use the sidebar to navigate, or start with Project Overview above.


Core & Project Overview

Top-level project context for GENIE.AI: scope, source-tree map, integration architecture, and contributor onboarding.

RAG Pipeline

Sovereign retrieval-augmented generation pipeline — embedding, hybrid vector-graph retrieval, reranking, generation, and optional translation.

Frontend (Gov-Chat Web)

Vue 3 + Vuex single-page app: UI component inventory, state-management patterns, and the theme system.

Backend (Gov-Chat API)

Node.js / Express backend: API contracts, auth flow, and service boundaries.

Mobile (genie_ai_mobile)

Flutter client: UI component inventory and mobile architecture.

Architecture

System-wide architecture: C4 container view, authentication flows, and the service-to-service auth matrix.

Deployment

End-to-end installation, Docker Compose / Swarm deployment, and GPU setup guides.

Configuration

Operator-facing configuration guides for Keycloak and external identity providers.

Observability

OpenTelemetry-native metrics, logs, and traces for the GENIE.AI stack — collection, storage, dashboards, and alerting.

Knowledge Base

Managing the GENIE.AI knowledge base — ingesting documents, the processing pipeline, the label taxonomy, document lifecycle, and content guidance.

Operations

Day-to-day operations for a running GENIE.AI deployment — backup and restore, updates, scaling, and troubleshooting.