FlareIgnis/SQLBot
🤖 Enhance data queries with SQLBot, an intelligent system that combines advanced models and RAG for seamless integration and secure access control.
What's novel
🤖 Enhance data queries with SQLBot, an intelligent system that combines advanced models and RAG for seamless integration and secure access control.
Code Analysis
24 files read · 6 roundsA FastAPI + Vue 3 web application that converts natural language questions into SQL queries by sending prompt-engineered requests to OpenAI-compatible LLM APIs, with embedding-based table/datasource selection, multi-database support (10+ types), chart generation, data analysis, and MCP server integr
Strengths
Genuinely multi-database support with per-dialect SQL handling, a well-structured modular backend with clean LLM factory pattern, and a functional multi-step pipeline (SQL → chart → analysis → prediction) with SSE streaming. The MCP server integration and permission-aware SQL generation show practical product thinking.
Weaknesses
Zero test coverage despite pytest being a dev dependency, a 72KB god-class (LLMService) handling all pipeline steps, a shared module-level DB session with a 200-thread pool creating race conditions, and significant business logic hidden in a proprietary sqlbot_xpack package from testpypi. The README describes a downloadable desktop app when it's actually a Docker-based web application.
Score Breakdown
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
1604
Contributors
19
Files
754
Active weeks
26
Repository
Language
Python
Stars
1
Forks
0
License
NOASSERTION