FalkorDB/QueryWeaver

An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.

What it solves

QueryWeaver is a Text2SQL tool that allows users to ask questions of their databases in plain English. It eliminates the need for users to manually write SQL queries by automatically converting natural language into executable SQL code and returning the results.

How it works

The system uses graph-powered schema understanding to map natural language questions to database structures. It supports multiple AI providers (OpenAI, Gemini, Anthropic, and Azure) to handle the translation. It can be deployed as a REST API, a Python SDK for direct integration, or an MCP (Model Context Protocol) server, allowing other AI services to interact with the database.

Who it’s for

It is designed for developers and data analysts who want to provide natural language interfaces to their SQL databases (PostgreSQL or MySQL) without requiring the end-user to know SQL.

Highlights

  • Graph-Powered Schema Understanding: Uses graphs to better understand the database schema for more accurate SQL generation.
  • Multi-LLM Support: Compatible with OpenAI, Gemini, Anthropic, and Azure OpenAI.
  • Flexible Deployment: Available as a standalone REST API, a Python SDK, or an MCP server.
  • Safety Mechanisms: Includes a confirmation step for destructive SQL operations (INSERT, UPDATE, DELETE).
  • Conversation Memory: Stores per-user conversation history in FalkorDB to maintain context across multiple queries.

Related

  • Project
    OtterMind/Chat2DB

    An AI-powered database client and SQL workspace that allows users to generate, explain, and optimize SQL queries using natural language across 40+ supported databases.

  • Project
    apconw/Aix-DB

    A conversational data analysis system (ChatBI) that uses LLMs and RAG to convert natural language queries into SQL and visual charts across multiple database types.

  • Project
    zhongyu09/openchatbi

    An open-source, chat-based BI tool that uses LLMs to convert natural language into SQL, enabling users to analyze and visualize database data through conversation.

  • Project
    dataease/SQLBot

    An intelligent data questioning system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language to SQL.

  • Dispatch
    Text2SQL with Hugging Face Dataset Viewer API and DuckDB-NSQL-7B

    Hugging Face demonstrates how to use the DuckDB-NSQL-7B model and the Dataset Viewer API to convert natural language questions into SQL queries for analyzing over 120,000 open datasets.