# dataease/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.

Repository: https://github.com/dataease/SQLBot
Canonical: https://ross.abutalabs.com/products/sqlbot
Homepage: https://sqlbot.org/
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: deepseek, llm, rag, sqlbot, text-to-sql, chatbi, nl2sql, text2sql
Last push: 2026-08-26T13:08:49+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 35
- inputs: {"age_days": 499, "days_push": 7, "days_rel": 6, "gap_med": 23, "n_releases_24m": 18}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6688, forks 851 (observed 2026-08-28T04:09:47.710143+00:00)

## What it is
SQLBot is an open-source conversational data analysis (ChatBI) system that converts natural language questions into SQL queries using large language models combined with RAG. It provides a web interface for querying databases, generating visualizations, and can be embedded into other applications or invoked via MCP.

## Use cases
- ask questions about my database in natural language
- text-to-sql generation with RAG
- chatbi conversational data analysis
- generate charts from natural language queries
- embed nl2sql querying into my app
- let non-technical users query a database safely
- connect deepseek or openai to my database for analytics

## When to choose
- you want a self-hosted, out-of-the-box ChatBI tool with Docker deployment
- you need fine-grained data permissions and workspace isolation for natural-language querying
- you want to embed text-to-SQL capabilities into apps like n8n, Dify, MaxKB, or DataEase
- you use OpenAI-compatible LLM providers (DeepSeek, Gemini, Kimi, etc.)

## When to avoid
- you need a general-purpose BI suite rather than conversational querying
- you cannot expose your database schema to an external LLM provider and don't want LLM involvement
- you need fully hand-tuned SQL with no generated queries

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, chatbot, data-visualization, database, prompt-engineering, mcp
- domain: large-language-models, databases, analytics, data-visualization, self-hosted
- platform: self-hosted, python
- tags: text-to-sql, nl2sql, chatbi, text2sql, conversational-analytics, bi, retrieval-augmented-generation, docker, linux, web-server

## Member repositories
- dataease/SQLBot (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:47.710143+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:42:59.233106+00:00, confidence not recorded.
  - readme: https://github.com/dataease/SQLBot (fetched 2026-08-28T04:09:47.710143+00:00, sha 38106f34e235)
  - homepage: https://sqlbot.org/ (fetched 2026-08-29T08:39:24.463526+00:00, sha 2d98219ea226)
  - site_page: https://sqlbot.org/docs (fetched 2026-08-29T08:39:24.472605+00:00, sha d6e01e8b64c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.