Aion
Aion is an AI-powered Bible companion that lets users ask questions about scripture in plain language. Responses are grounded in actual Bible data retrieved via a Hybrid RAG pipeline combining keyword matching and semantic vector search (pgvector), then streamed in real time via SSE from Gemini. The app runs on mobile (React Native + Expo) and desktop (Tauri v2).
01 / Overview
- 01React Native 0.81
- 02Expo 54
- 03TypeScript
- 04Supabase PostgreSQL
- 05pgvector
- 06OpenAI Embeddings
- 07Gemini 3.1 Flash
- 08Tauri v2
- 09TanStack Query v5
- 10NativeWind
Problem
Bible study tools are either keyword-only search engines that miss semantic meaning, or AI chatbots that hallucinate verses. Users need conversational AI that is genuinely grounded in scripture with verifiable citations.
Solution Overview
- Built a Hybrid RAG pipeline combining regex-based keyword extraction with OpenAI embedding (1536-dim) + pgvector semantic search
- Implemented real-time SSE streaming from Gemini via Supabase Edge Functions
- Designed rich inline verse cards with full book/chapter/verse attribution for verifiability
- Added cross-platform support: React Native for mobile + Tauri v2 for native desktop
02 / Evidence
Proof & Verification
- Hybrid RAG retrieval ensures answers are grounded in actual scripture, not hallucinated
- IP-based rate limiting (5/min burst, 30/3hrs, 200/day) with fail-closed defaults
- Exact-match response cache eliminates redundant LLM costs
- Anonymous authentication with no sign-up; Supabase RLS applies to all tables
Research Papers
Papers: 1Aion-BibleQA: Evaluating Retrieval and Citation Faithfulness in Verse-Grounded Bible RAG Systems
8-page paper introducing a 40-question Bible RAG benchmark for citation faithfulness and false-premise robustness, with v3 retrieval reaching R@5 = 0.941, mean citation_support = 0.978, zero unsupported citations, and 6/6 false-premise refusals.
Download Paper03 / Methods
Build
Tech Stack
- React Native 0.81
- Expo 54
- TypeScript
- Supabase PostgreSQL
- pgvector
- OpenAI Embeddings
- Gemini 3.1 Flash
- Tauri v2
- TanStack Query v5
- NativeWind
- Hybrid RAG pipeline: regex keyword extraction + OpenAI embedding (1536-dim) + pgvector semantic search
- Real-time SSE streaming from Gemini via Supabase Edge Functions
- Rich inline verse cards with book/chapter/verse attribution
- Cross-platform: React Native (iOS/Android) + Tauri v2 (macOS/Windows/Linux)
Secure
- All API keys (OpenAI, Gemini, service_role) stored server-side only in Edge Function secrets
- IP-based rate limiting: 5/min burst, 30/3hrs per IP, 200/day global cap
- Row-Level Security (RLS) on all Supabase tables
- 500-character message length cap to prevent token-stuffing
- Exact-match response cache (zero LLM cost on repeated queries)
- Fail-closed: rate limit errors default to deny