Architecture Overview
YUIEN is powered by Amazon Web Services (AWS) and leverages cutting-edge AI technology to deliver fast, accurate, and source-grounded responses.
🧠 AI Foundation Model
We use Claude 3 Haiku (Anthropic) via AWS Bedrock — a state-of-the-art large language model known for:
- Fast responses: Under 2 seconds average
- Contextual understanding: Maintains conversation flow naturally
- Multilingual capability: Native support for 6+ languages
- Source grounding: Retrieves from knowledge base, not invented content
📚 Knowledge Base
YUIEN's knowledge is stored in AWS Bedrock Knowledge Base, powered by:
- Vector Database: Amazon OpenSearch Serverless
- Embeddings: Titan Text Embeddings V2
- 202+ Documents: PDFs, DOCX, web content
- Semantic Search: Finds relevant passages even with different wording
- Source Attribution: Every response includes document citations
☁️ Infrastructure
AWS Lambda
Serverless API endpoint — scales automatically, zero maintenance
API Gateway
RESTful API with CORS support for web integration
Amazon S3
Document storage with versioning and backup
CloudWatch
Monitoring, logging, and performance metrics
🔒 Security & Privacy
- No conversation storage: Your questions are not saved or logged
- IAM role-based access: Strict permissions on AWS resources
- HTTPS encryption: All API traffic is encrypted in transit
- No third-party tracking: No analytics, ads, or cookies
- Open source (soon): Code will be publicly auditable
💰 Cost Efficiency
YUIEN operates on a pay-per-use model with AWS free tier credits:
- $120 USD in free credits (valid until August 2026)
- Estimated monthly cost: $14-25 USD after credits expire
- No upfront investment: Pay only for actual usage
- Auto-scaling: Handles 1 user or 1,000 users without code changes
📊 Performance Metrics
| Average Response Time | <2 seconds |
| Knowledge Base Size | 202+ documents |
| Supported Languages | 6 (EN, PT, JP, ES, FR, DE) |
| API Timeout | 30 seconds |
| Uptime (Target) | 99.9% |
🔮 Future Enhancements
On our roadmap:
- Voice interface: Ask questions via speech
- Mobile app: Native iOS and Android apps
- API access: Integrate YUIEN into temple websites
- Advanced search: Filter by text type, author, time period
- Personalization: Remember conversation context across sessions
- Expanded corpus: More languages, more texts
Technical Questions?
Interested in the technical details, want to contribute code, or planning to deploy YUIEN for your temple? We're happy to share documentation and support your implementation.
Contact Technical Team