SuperSonic is an AI+BI platform unifying Chat BI (LLM-powered natural language querying) and Headless BI (semantic layer) paradigms. It targets analytics engineers and business users, enabling natural language data exploration with governed semantic models and providing a unified, context-aware query experience.

How It Works

SuperSonic integrates LLM-based Text2SQL with a semantic layer to improve query reliability and context. It augments LLM prompts with semantic model details (business terms, column values) and offloads complex SQL generation (joins, formulas) to the semantic layer. This approach aims to reduce LLM hallucinations and simplify query complexity.

Quick Start & Requirements

• Docker: wget https://raw.githubusercontent.com/tencentmusic/supersonic/master/docker/docker-compose.yml followed by docker-compose up -d. Access via http://localhost:9080.
• Local Build: Download prebuilt binary from releases, run assembly/bin/supersonic-daemon.sh start. Access via http://localhost:9080.
• Prerequisites: Docker, Java.
• Demo: Online playground available at http://117.72.46.148:9080.

Highlighted Details

• Built-in Chat BI and Headless BI interfaces.
• Supports input auto-completion, multi-turn conversations, and post-query recommendations.
• Implements three-level data access control (dataset, column, row).
• Extensible via Java SPI for custom components.

Maintenance & Community

• Official WeChat account for contact.
• Project documentation available.

Licensing & Compatibility

• License not explicitly stated in the README.

Limitations & Caveats

The README does not specify the license, which is a critical factor for commercial adoption. The online demo is for demonstration purposes and system configurations are reset regularly.