Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
Siqiao Xue, Danrui Qi, Caigao Jiang, Wenhui Shi, Fangyin Cheng, Keting Chen, Hongjun Yang, Zhiping Zhang, Jianshan He, Hongyang Zhang, Ganglin Wei, Wang Zhao, Fan Zhou, Hong Yi, Shaodong Liu, Hongjun Yang, Faqiang Chen
TL;DR
DB-GPT addresses the need for a task-agnostic, privacy-preserving data-interaction interface powered by large language models. It introduces a four-layer architecture and three core innovations: a Multi-Agents Framework for autonomous task planning, the declarative Agentic Workflow Expression Language (AWEL) for workflow specification, and the Service-oriented Multi-model Framework (SMMF) for private LLM deployment with Retrieval-Augmented Generation from multiple data sources. The library supports a broad range of data-interaction tasks (Text-to-SQL, chat-to-db, chat-to-data, chat-to-Excel, chat-to-visualization, generative data analysis) and offers product-ready features like drag-and-drop AWEL construction, multilingual support, and local/private model deployment. By enabling end-to-end data interaction across local, distributed, and cloud environments, DB-GPT aims to empower developers and businesses to harness AI-driven data insights with improved privacy and flexibility.
Abstract
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software. The technologies of interacting with data particularly have an important entanglement with LLMs as efficient and intuitive data interactions are paramount. In this paper, we present DB-GPT, a revolutionary and product-ready Python library that integrates LLMs into traditional data interaction tasks to enhance user experience and accessibility. DB-GPT is designed to understand data interaction tasks described by natural language and provide context-aware responses powered by LLMs, making it an indispensable tool for users ranging from novice to expert. Its system design supports deployment across local, distributed, and cloud environments. Beyond handling basic data interaction tasks like Text-to-SQL with LLMs, it can handle complex tasks like generative data analysis through a Multi-Agents framework and the Agentic Workflow Expression Language (AWEL). The Service-oriented Multi-model Management Framework (SMMF) ensures data privacy and security, enabling users to employ DB-GPT with private LLMs. Additionally, DB-GPT offers a series of product-ready features designed to enable users to integrate DB-GPT within their product environments easily. The code of DB-GPT is available at Github(https://github.com/eosphoros-ai/DB-GPT) which already has over 10.7k stars. Please install DB-GPT for your own usage with the instructions(https://github.com/eosphoros-ai/DB-GPT#install) and watch a 5-minute introduction video on Youtube(https://youtu.be/n_8RI1ENyl4) to further investigate DB-GPT.