Commit Graph

8 Commits

Author SHA1 Message Date
a01377b21a feat: implement AI chat with vector search and random loading messages
Major Features:
-  AI chat with Azure OpenAI GPT-4o integration
-  Vector search across Bible versions (ASV English, RVA 1909 Spanish)
-  Multi-language support with automatic English fallback
-  Bible version citations in responses [ASV] [RVA 1909]
-  Random Bible-themed loading messages (5 variants)
-  Safe build script with memory guardrails
-  8GB swap memory for build safety
-  Stripe donation integration (multiple payment methods)

AI Chat Improvements:
- Implement vector search with 1536-dim embeddings (Azure text-embedding-ada-002)
- Search all Bible versions in user's language, fallback to English
- Cite Bible versions properly in AI responses
- Add 5 random loading messages: "Searching the Scriptures...", etc.
- Fix Ollama conflict (disabled to use Azure OpenAI exclusively)
- Optimize hybrid search queries for actual table schema

Build & Infrastructure:
- Create safe-build.sh script with memory monitoring (prevents server crashes)
- Add 8GB swap memory for emergency relief
- Document build process in BUILD_GUIDE.md
- Set Node.js memory limits (4GB max during builds)

Database:
- Clean up 115 old vector tables with wrong dimensions
- Keep only 2 tables with correct 1536-dim embeddings
- Add Stripe schema for donations and subscriptions

Documentation:
- AI_CHAT_FINAL_STATUS.md - Complete implementation status
- AI_CHAT_IMPLEMENTATION_COMPLETE.md - Technical details
- BUILD_GUIDE.md - Safe building guide with guardrails
- CHAT_LOADING_MESSAGES.md - Loading messages implementation
- STRIPE_IMPLEMENTATION_COMPLETE.md - Stripe integration docs
- STRIPE_SETUP_GUIDE.md - Stripe configuration guide

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-12 19:37:24 +00:00
79f1512f3a feat: Apple-style donation-focused landing page + Azure OpenAI fixes
Major updates:
- Replace homepage with clean, minimalist Apple-style landing page
- Focus on donation messaging and mission statement
- Add comprehensive AI chat analysis documentation
- Fix Azure OpenAI configuration with correct endpoints
- Update embedding API to use text-embedding-ada-002 (1536 dims)

Landing Page Features:
- Hero section with tagline "Every Scripture. Every Language. Forever Free"
- Mission statement emphasizing free access
- Matthew 10:8 verse highlight
- 6 feature cards (Global Library, Multilingual, Prayer Wall, AI Chat, Privacy, Offline)
- Donation CTA sections with PayPal and card options
- "Why It Matters" section with dark background
- Clean footer with navigation links

Technical Changes:
- Updated .env.local with new Azure credentials
- Fixed vector-search.ts to support separate embed API version
- Integrated AuthModal into Bible reader and prayers page
- Made prayer filters collapsible and mobile-responsive
- Changed language picker to single-select

Documentation Created:
- AI_CHAT_FIX_PLAN.md - Comprehensive implementation plan
- AI_CHAT_VERIFICATION_FINDINGS.md - Database analysis
- AI_CHAT_ANALYSIS_SUMMARY.md - Executive summary
- AI_CHAT_STATUS_UPDATE.md - Current status and next steps
- logo.svg - App logo (MenuBook icon)

Build:  Successful (Next.js 15.5.3)

🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-10 22:38:19 +00:00
e4b815cb40 Add Ollama embedding support and improve prayer system with public/private visibility
- Add Ollama fallback support in vector search with Azure OpenAI as primary
- Enhance prayer system with public/private visibility options and language filtering
- Update OG image to use new biblical-guide-og-image.png
- Improve prayer request management with better categorization
- Remove deprecated ingest_json_pgvector.py script

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-28 19:25:49 +00:00
2d27eae756 Enhance RAG system to support multiple vector databases and improve AI chat functionality
- Update vector-search.ts to query all available vector tables per language instead of single table
- Add getAllVectorTables() function to discover all language-specific vector tables
- Enhance searchBibleHybrid() to query multiple tables and merge results by relevance score
- Enhance searchBibleSemantic() to combine results from all available vector databases
- Add comprehensive error handling and logging for vector search operations
- Improve Azure OpenAI content filtering detection and error handling
- Add test-vector API endpoint for database diagnostics and debugging
- Fix environment configuration with complete Azure OpenAI settings
- Enable multi-translation biblical context from diverse Bible versions simultaneously

Tested: Romanian chat works excellently with rich biblical context and verse citations
Issue: English requires vector table creation - 47 English Bible versions exist but no vector tables

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-25 07:21:59 +00:00
andupetcu
196ca00194 Fix authentication state persistence and admin role display
- Implement complete authentication system with JWT token validation
- Add auth provider with persistent login state across page refreshes
- Create multilingual login/register forms with Material-UI components
- Fix token validation using raw SQL queries to bypass Prisma sync issues
- Add comprehensive error handling for expired/invalid tokens
- Create profile and settings pages with full i18n support
- Add proper user role management (admin/user) with database sync
- Implement secure middleware with CSRF protection and auth checks
- Add debug endpoints for troubleshooting authentication issues
- Fix Zustand store persistence for authentication state

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-21 01:06:30 +03:00
andupetcu
5ddf62e5cf Vector schema per version: add ai_bible schema with per-version tables (bv_<lang>_<abbr>) in Python ingest; dynamic table resolution in vector-search with fallback to legacy table; sample pgAdmin queries printed. 2025-09-20 19:08:11 +03:00
andupetcu
a0969e88df Implement complete multi-language support with Romanian/English
- Added next-intl for internationalization with Romanian as default locale
- Restructured app directory with [locale] routing (/ro, /en)
- Created comprehensive translation files for both languages
- Fixed Next.js 15 async params compatibility in layout components
- Updated all components to use proper i18n hooks and translations
- Configured middleware for locale routing and fallbacks
- Fixed FloatingChat component translation array handling
- Restored complete home page with internationalized content
- Fixed Material-UI Slide component prop error (mountOnExit → unmountOnExit)

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-20 15:43:51 +03:00
andupetcu
dd5e1102eb Implement Azure OpenAI vector embeddings for Romanian Bible
- Add pgvector support with bible_passages table for vector search
- Create Python ingestion script for Azure OpenAI embed-3 embeddings
- Implement hybrid search combining vector similarity and full-text search
- Update AI chat to use vector search with Azure OpenAI gpt-4o
- Add floating chat component with Material UI design
- Import complete Romanian Bible (FIDELA) with 30K+ verses
- Add vector search library for semantic Bible search
- Create multi-language implementation plan for future expansion

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-09-20 15:18:00 +03:00