LingxiBI
AI-powered data analytics & reporting platform that connects databases and generates interactive dashboards via natural language queries.
Ficha actualizada 22 sept 2026, 18:30 · upstream 22 sept 2026, 18:10 · release Lx-1.1.0
Qué es LingxiBI
Descripción editorial construida a partir del repositorio, su documentación y sus señales de mantenimiento.
HISENSE LingxiBI is a self-learning BI platform that turns raw databases into shareable, interactive dashboards without requiring SQL knowledge or traditional BI tools. Users connect MySQL, PostgreSQL, or Oracle databases through simple conversations in plain English. The AI learns your business context over time by extracting new rules and examples from your interactions. It generates responsive ECharts HTML dashboards with version history, supports multi-channel alert delivery (email + Feishu), and offers a curated metrics library as an AI knowledge base. Designed for intuitive understanding between users and data.
- Automatically generate interactive dashboard reports from raw database tables without SQL expertise
- Create natural language queries to explore data, with the system learning your business context over time
- Build personalized dashboards by refining prompts conversationally rather than writing complex SQL
- Set up automated alerting via email or Feishu (Lark) when metrics exceed defined thresholds
- Share report links securely while maintaining version history and audit trails
- Create multi-language reports with full i18n support for international teams
- Supports MySQL, PostgreSQL, and Oracle databases through auto-introspection of schemas and relationships as a knowledge graph
- Self-learning architecture that accumulates business knowledge per datasource, making queries more accurate over time
- Generates fully responsive ECharts HTML dashboards with conversational refinement and version history
- Multi-channel alert delivery via SMTP (with Excel export) or Feishu interactive cards with HMAC-SHA256 signed links
- Curated metrics library that doubles as a knowledge base, allowing AI to reference validated business definitions
- Self-serve access control with role-based permissions and per-user ownership of reports, metrics, conversations, and alerts
- Requires an external LLM API (OpenAI-compatible) for query generation; no built-in SQL engine or database connectivity
- Alerts are email-based only via SMTP; Feishu integration requires a webhook endpoint with HMAC-SHA256 signing
- No real-time data streaming capability — dashboards and alerts rely on scheduled snapshots rather than live data feeds
- Self-learning depends on user interaction quality; unhelpful queries may not trigger new knowledge extraction
- MySQL/MariaDB is the only supported metadata database; PostgreSQL/Oracle require manual schema introspection configuration
Perfil de infraestructura
Estimación inicial derivada del repositorio y de los servicios detectados.
Despliegue detectado
Qué señales reales de instalación hemos encontrado.
Deploy as a Rust (Axum) server with MySQL metadata storage, Nginx reverse proxy for SPA hosting, and TLS termination. Use `scripts/setup-server.sh` to install toolchain, MySQL, Nginx, and TLS on the target host. Deploy via `./scripts/deploy.sh user@host [domain]`. Configure CORS origins in production. For multi-instance deployments, use atomic background job scheduling (e.g., cron) for snapshot generation and alert delivery to avoid race conditions.
Stack y dependencias
Componentes inferidos a partir de manifests, configuración y documentación.
Puede sustituir a
Relaciones detectadas por el análisis del repositorio y su categoría.
Experiencia real de la comunidad
Ayuda a contrastar la estimación automática con instalaciones reales.
Todavía no hay datos comunitarios para este proyecto.