// Generated by orrery. Edit the diagram spec and re-render instead of editing this file. import { type SVGProps, useId } from "react"; export default function OpenSourceDataPlatform(props: SVGProps) { const uid = useId().replace(/[^A-Za-z0-9_-]/g, ""); return ( Open-source data platform Open-source data platform. 13 components in 6 groups. Connections: SaaS APIs to Airbyte (REST API); Airbyte to Apache Kafka (community destination); PostgreSQL to Debezium (WAL); MySQL to Debezium (binlog); Debezium to Apache Kafka; Apache Kafka to Apache Flink; Apache Flink to Apache Iceberg (Iceberg sink); Apache Flink to Hive Metastore (commit); Apache Iceberg to Trino (read data files); Hive Metastore to Trino (look up tables); Apache Airflow to dbt (dbt run); dbt to Trino (SQL models); Trino to Apache Superset. OPEN-SOURCE DATA PLATFORM Debezium and Airbyte feed Kafka, Flink lands the streams as Iceberg tables on Ceph, and dbt models them on Trino for Superset on an Airflow schedule REST API REST API COMMUNITY DESTINATION COMMUNITY DESTINATION WAL BINLOG ICEBERG SINK ICEBERG SINK COMMIT READ DATA FILES READ DATA FILES LOOK UP TABLES LOOK UP TABLES DBT RUN SQL MODELS SOURCES INGEST STORE TRANSFORM SERVE CEPH OBJECT GATEWAY APACHE AIRFLOW Orchestration DBT SQL models on Trino SAAS APIS CRM and billing POSTGRESQL Orders MYSQL Inventory AIRBYTE API syncs DEBEZIUM Change data capture APACHE KAFKA Event streams APACHE FLINK Stream processing APACHE ICEBERG Lakehouse tables HIVE METASTORE Iceberg catalog TRINO Reads and writes tables APACHE SUPERSET Dashboards DATA FLOW ORCHESTRATION AND SQL ); }