DeepBI is an AI-native data analysis platform enabling conversational data analysis, query generation, dashboards, and multi-source data connections. It supports Windows, Linux, Mac, and various databases, with Docker and Windows installer options.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
DeepBI is an AI-native data analysis platform. DeepBI leverages large language models to explore, query, visualize, and share data from multiple data sources.
How it works
Features include conversational data analysis, conversational query generation, and dashboards. It supports multiple data sources (MySQL, PostgreSQL, CSV/Excel, Doris, StarRocks, MongoDB) and runs across Windows, WSL, Linux, and Mac. It provides automated data analysis reports (to be developed).
Getting started
Windows exe installation
- Download
window_install_exe_EN.zipfrom the <a href="https://github.com/DeepInsight-AI/DeepBI/releases">tag list</a>. - Unzip the zip package and double-click the.exe file to run DeepBI
- Local installation instructions Installl exe
Docker build
- The local environment needs Docker and docker-compose.
- Clone the repo:
git clone https://github.com/DeepInsight-AI/DeepBI.git - Enter project directory:
cd DeepBI - Run:
./Install.sh - Default port: 8338 8339
- Web access: http://ip:8338
Docker commands
docker-compose start
docker-compose stop
docker-compose ps
If permission errors occur, prepend with sudo:
sudo docker-compose start
sudo docker-compose stop
sudo docker-compose ps
Ubuntu build
- Install Redis, PostgreSQL, Python 3.8.x
- PostgreSQL version: 16
- Clone:
git clone https://github.com/DeepInsight-AI/DeepBI.git - If clone fails, use:
git clone http://github.com/DeepInsight-AI/DeepBI.git - Run:
. ubuntu_install.sh - Default port: 8338 and 8339
- Web access: http://ip:8338
Recent releases
- v2.0.4 (2024-10-08): Modify the api service domain name; Fix the bug of invate code; Modify default llm config
- v2.0.3 (2024-06-21): Fix picture generation in report dialog; fix function search in auxiliary data analysis dialog; added csv automatic data anal
- v2.0.2 (2024-06-14): Adapt an existing function call to the new openai version of tools
- v2.0.1 (2024-06-12): Added Ali Bailian, Baidu Qianfan LLM; wrap English status; exe startup problem
- v2.0.0 (2024-05-31): Added different llm configurations, including OpenAI, DeepInsight, AzureOpenAI, AwsClaude, DeepSeek
Traction
- The repository has 2365 stars and 370 forks; 71 open issues
Behind the repo
- Not provided in the README excerpt
Caveats
- License: MIT
- Created: 2023-11-20; last push: 2025-04-14
- Primary language: Python
- Supported data sources: MySQL, PostgreSQL, CSV/Excel, Doris, StarRocks, MongoDB