RAG & Knowledge
DB-GPT
An agentic AI data assistant - chat with your databases, run SQL and code, get reports
★ 20.1k starsMIT
View guide →LibreAI / RAG & Knowledge / SQLBot
// rag · dataease/SQLBot
SQLBot
SQLBot is an open-source rag & knowledge project by dataease (dataease/SQLBot on GitHub). It has 6,875 GitHub stars and 893 forks, is released under the GPL-3.0 license, and was last updated on GitHub on 8 October 2026.
SQLBot — DataEase's conversational analytics: ask in natural language, get SQL answers via LLMs plus RAG.
★ 6.9k stars⑂ 893 forksGPL-3.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- dataease/SQLBot
- GitHub stars
- 6,875
- Forks
- 893
- License
- GPL-3.0
- Last updated on GitHub
- 8 October 2026
- Category
- RAG & Knowledge
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Clarify your goal
Choose the LLM you will connect and the first data source, and plan your workspace and permission boundaries before inviting users.
- Get the project
Clone dataease/SQLBot from GitHub (or use the install path in the run steps below) and skim its README for the parts relevant to your goal.
- Install and configure
Run the documented Docker container with its ports and data volumes, then open the web UI to configure your model and data source.
- Run your first task
Add one table you know well, ask a question in natural language, and verify the generated SQL and answer against a hand-written query.
// features
Why people love it
Conversational Text-to-SQL
Natural-language questions become SQL using LLM understanding plus RAG, with no complex development to get started.
Workspace isolation and permissions
Workspace-level resource isolation and fine-grained data permissions keep access bounded and compliant.
Many embedding options
Embed via web, popup or MCP calls, and integrate quickly with n8n, Dify, MaxKB, DataEase and similar apps.
Improves with use
Custom prompts, a terminology library and SQL examples calibrate it to your business, and interaction data drives continued tuning.
Simple configuration
Only a model and a data source need configuring before users can start asking questions.
Part of the DataEase ecosystem
From the team behind DataEase, designed to give existing BI-style deployments a conversational query front end.
Advertisement
// run it
Run it yourself
- Clone the repository
Get the source from the official GitHub repository for SQLBot.
git clone https://github.com/dataease/SQLBot.git cd SQLBot - Run SQLBot with Docker
Start the container with the documented ports and data volumes from the README.
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/sqlbot - Configure and ask
Open the web access address from the README, configure your large model and data source, then ask your first question.
# Open the SQLBot web UI (ports above), add model + data source — see README access section
// use cases
What you can build
- Letting operations staff ask 'last month's sales by region' without writing SQL
- Embedding conversational analytics into an existing portal via the embed or MCP options
- Giving analysts a first-draft SQL generator calibrated with your terminology and examples
- Adding a chat front end to a DataEase deployment for business users
Advertisement
// faq
Questions, answered
Who maintains SQLBot?
dataease (FIT2CLOUD), through the dataease/SQLBot repository, with the site at sqlbot.org.
Is SQLBot free to use?
Yes — the project is open source under the GPL-3.0 license as recorded for this listing. See the license terms for any conditions on redistribution.
Does SQLBot need a paid API key?
You configure your own large model for it to call, so model usage is under your credentials; SQLBot itself is open source under its FIT2CLOUD license (GPLv3-based, per its README).
How does SQLBot compare to a general AI chat tool with a database plugin?
Generic chat tools can generate SQL, but SQLBot is purpose-built for querying: workspace isolation, fine-grained data permissions, terminology/SQL-example calibration and embed/MCP delivery for analytics products.
How do I get started with SQLBot?
Clone the repository (or use the documented installer), follow the install and configure steps on this page, and run the smallest real task first — add one table you know well, ask a question in natural language, and verify the generated SQL and answer against a hand-written query.
// keep exploring
Similar tools
RAG & Knowledge
rags
Build a ChatGPT over your own data using natural language and LlamaIndex.
★ 6.5k starsMIT
View guide →RAG & Knowledge
code-graph-rag
RAG for your monorepo: query, understand and edit multi-language codebases with a knowledge graph.
★ 5.2k starsMIT
View guide →RAG & Knowledge
swirl-search
Federated AI search and RAG across 100+ apps — answers with sources, without moving your data
★ 3.0k starsApache-2.0
View guide →RAG & Knowledge
trieve
All-in-one API platform for search, recommendations, RAG and analytics — self-hostable
★ 2.7k starsMIT
View guide →RAG & Knowledge
private-gpt
Complete API layer for private AI apps on local models: RAG, skills, tools, MCP and text-to-SQL
★ 57.6k starsApache-2.0
View guide →// alternatives
Alternatives in RAG & Knowledge
The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if SQLBot is not the right fit.
- MarkItDown★ 193.5k
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
- Dify★ 157.8k
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
- MinerU★ 82.5k
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
// more in rag
More in RAG & Knowledge
Nearby RAG & Knowledge projects in the catalogue, closest in stars to SQLBot — keep exploring the shelf either side of it.
- vespa★ 7.1k
Vespa — the AI search platform: vector, text and tensor search at production scale.
- rags★ 6.5k
Build a ChatGPT over your own data using natural language and LlamaIndex.
- unstract★ 7.3k
Unstract — LLM-driven extraction of unstructured data, built for API deployments and ETL pipeline workflows.
- helix-db★ 6.1k
An OLTP graph database with native vector and full-text search, built in Rust on object storage.
- deep-searcher★ 8.3k
DeepSearcher — open-source deep research over your private data, with reasoning models and Milvus retrieval.
- UltraRAG★ 5.7k
A low-code MCP framework for building complex, innovative RAG pipelines — visibly, not as a black box.
Get SQLBot
Free and open — grab the source, star the repo, and start creating.