DB-GPT: Empowering Database Interactions with Private Large Language Models (2312.17449v2)
Abstract: The recent breakthroughs in 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.
- Palm 2 technical report. arXiv preprint arXiv:2305.10403, 2023.
- Qwen technical report. arXiv preprint arXiv:2309.16609, 2023.
- Baichuan. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305, 2023.
- Language models are few-shot learners. Advances in Neural Information Processing Systems (NeurIPS), 2020.
- KQA pro: A dataset with explicit compositional programs for complex question answering over knowledge base. In Muresan, S., Nakov, P., and Villavicencio, A. (eds.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6101–6119, Dublin, Ireland, May 2022. Association for Computational Linguistics.
- Chase, H. LangChain, 2022.
- Evaluating large language models trained on code, 2021.
- Palm: Scaling language modeling with pathways, 2022.
- Leveraging large language models for pre-trained recommender systems. arXiv preprint arXiv:2308.10837, 2023.
- A survey on in-context learning. 2022.
- Group, A. OceanBase, 2021.
- Textbooks are all you need. arXiv preprint arXiv:2306.11644, 2023.
- H2O.ai. H2OGPT, May 2023.
- Metagpt: Meta programming for multi-agent collaborative framework, 2023.
- Chatdb: Augmenting llms with databases as their symbolic memory, 2023.
- Huggingface. Text Generation Inference, May 2021.
- Towards anytime fine-tuning: Continually pre-trained language models with hypernetwork prompt. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
- Large models for time series and spatio-temporal data: A survey and outlook, 2023.
- Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023.
- Complex knowledge base question answering: A survey, 2022.
- Retrieval-augmented generation for knowledge-intensive nlp tasks. ArXiv, abs/2005.11401, 2020.
- A comprehensive evaluation of chatgpt’s zero-shot text-to-sql capability, 2023.
- Liu, J. LlamaIndex, 11 2022.
- PrivateGPT, May 2023.
- MongoDB. MongoDB.
- MySQL. MySQL.
- Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332, 2021.
- NVIDIA. TensorRT, May 2021.
- OpenAI. GPT-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
- Deep optimal timing strategies for time series. In ICDM, 2023.
- Bellman meets hawkes: Model-based reinforcement learning via temporal point processes. In Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
- Richards, T. B. Autogpt, 2022.
- Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761, 2023.
- Language models can improve event prediction by few-shot abductive reasoning. In Advances in Neural Information Processing Systems, 2023.
- skypilot org. Skypilot, 2022.
- Sql-palm: Improved large language model adaptation for text-to-sql, 2023.
- Llama 2: Open foundation and fine-tuned chat models, 2023.
- Identity-based proxy-oriented data uploading and remote data integrity checking in public cloud. IEEE Transactions on Information Forensics and Security, 11(6):1165–1176, 2016.
- Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533, 2022a.
- Enhancing recommender systems with large language model reasoning graphs. arXiv preprint arXiv:2308.10835, 2023.
- Learning to prompt for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 139–149, 2022b.
- Emergent abilities of large language models, 2022.
- A graph regularized point process model for event propagation sequence. In IJCNN, pp. 1–7, 2021.
- A meta reinforcement learning approach for predictive autoscaling in the cloud. In Zhang, A. and Rangwala, H. (eds.), KDD ’22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022, pp. 4290–4299. ACM, 2022a.
- Hypro: A hybridly normalized probabilistic model for long-horizon prediction of event sequences. In Advances in Neural Information Processing Systems, 2022b.
- Easytpp: Towards open benchmarking the temporal point processes. 2023a.
- Prompt-augmented temporal point process for streaming event sequence. In NeurIPS, 2023b.
- Weaverbird: Empowering financial decision-making with large language model, knowledge base, and search engine, 2023c.
- ReAct: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR), 2023.
- Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 2018. Association for Computational Linguistics.
- Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414, 2022.
- Calibrate before use: Improving few-shot performance of language models. arXiv preprint arXiv:2102.09690, 2021.
- Judging llm-as-a-judge with mt-bench and chatbot arena, 2023.
- Llm as dba, 2023.