SQLBot

🔥 基于大模型和 RAG 的智能问数系统,对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.

What is SQLBot?

🔥 基于大模型和 RAG 的智能问数系统,对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.

Overview of SQLBot

What it is

SQLBot is an intelligent query system based on large language models and RAG (Retrieval-Augmented Generation). It is developed by the DataEase open source project team. With SQLBot, users can perform conversational data analysis (ChatBI), quickly extract required data information and visual charts, and further conduct intelligent analysis.

Key features

  • Out-of-the-box: Only simple configuration of the large model and data source is needed; no complex development is required to start intelligent querying. It leverages the natural language understanding and SQL generation capabilities of large models, combined with RAG technology, to achieve high-quality Text-to-SQL conversion.
  • Secure and controllable: Provides workspace-level resource isolation to build clear data boundaries and ensure data access security. Supports fine-grained data permission configuration to strengthen permission control and ensure compliance.
  • Easy to integrate: Supports multiple integration methods, including web embedding, popup embedding, and MCP invocation. It can be quickly embedded into applications such as n8n, Dify, MaxKB, and DataEase.
  • Improves with use: Supports custom prompts, terminology library configuration, and maintainable SQL example calibration logic to accurately match business scenarios. Based on user interaction data, the query effect improves iteratively with use.

Use cases

SQLBot is suitable for scenarios where users need to query databases using natural language without writing SQL. It can be used for business intelligence reporting, data exploration, and embedding intelligent query capabilities into existing applications.

Getting started

Prepare a Linux server with Docker installed, then run the following one-click installation script:docker run -d --name sqlbot --restart unless-stopped -p 8000:8000 -p 8001:8001 -v ./data/sqlbot/excel:/opt/sqlbot/data/excel -v ./data/sqlbot/file:/opt/sqlbot/data/file -v ./data/sqlbot/images:/opt/sqlbot/images -v ./data/sqlbot/logs:/opt/sqlbot/app/logs -v ./data/postgresql:/var/lib/postgresql/data --privileged=true dataease/sqlbotYou can also deploy SQLBot quickly via the 1Panel app store. For intranet environments, an offline installation package is available.

License and pricing

SQLBot is open source. It follows the FIT2CLOUD Open Source License, which is essentially GPLv3 with additional restrictions. The license requires that the Logo and copyright information of SQLBot not be replaced or modified, and that derivative works comply with GPL V3 obligations. Pricing is not stated.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/dataeasesqlbot.svg)](https://yunodb.com/tools/dataeasesqlbot?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/dataeasesqlbot?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/dataeasesqlbot.svg" alt="Featured on YunoDB" height="20"></a>