DB-GPT: Empowering Database Interactions with Private Large Language Models

TL;DR

DB-GPT tackles the challenge of private, natural-language database access by integrating privacy-preserving LLMs with a retrieval-augmented generation (RAG) pipeline and a service-oriented multi-model framework (SMMF). It introduces a multi-source RAG workflow with knowledge construction, retrieval, and adaptive ICL, backed by bilingual encoders and Text-to-SQL fine-tuning to translate natural language into SQL. The system is extended with configurable agents and database plugins, enabling end-to-end data analytics without data leakage. Experimental results across Text-to-SQL, RAG, and SMMF demonstrate improved SQL generation quality, robust cross-domain QA, and substantial throughput/latency gains from using vLLM, underscoring the practicality of private, scalable NL-database interactions for diverse users.

Abstract

The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software. Database technologies particularly have an important entanglement with LLMs as efficient and intuitive database interactions are paramount. In this paper, we present DB-GPT, a revolutionary and production-ready project that integrates LLMs with traditional database systems to enhance user experience and accessibility. DB-GPT is designed to understand natural language queries, provide context-aware responses, and generate complex SQL queries with high accuracy, making it an indispensable tool for users ranging from novice to expert. The core innovation in DB-GPT lies in its private LLM technology, which is fine-tuned on domain-specific corpora to maintain user privacy and ensure data security while offering the benefits of state-of-the-art LLMs. We detail the architecture of DB-GPT, which includes a novel retrieval augmented generation (RAG) knowledge system, an adaptive learning mechanism to continuously improve performance based on user feedback and a service-oriented multi-model framework (SMMF) with powerful data-driven agents. Our extensive experiments and user studies confirm that DB-GPT represents a paradigm shift in database interactions, offering a more natural, efficient, and secure way to engage with data repositories. The paper concludes with a discussion of the implications of DB-GPT framework on the future of human-database interaction and outlines potential avenues for further enhancements and applications in the field. The project code is available at https://github.com/eosphoros-ai/DB-GPT. Experience DB-GPT for yourself by installing it with the instructions https://github.com/eosphoros-ai/DB-GPT#install and view a concise 10-minute video at https://www.youtube.com/watch?v=KYs4nTDzEhk.

Figures (7)

• Figure 1: The architecture of DB-GPT
• Figure 2: The detailed RAG architecture in DB-GPT
• Figure 3: The pipeline of knowledge construction
• Figure 4: The pipeline of knowledge retrieval
• Figure 5: The pipeline of adaptive ICL and response generation