{"id":13754193,"url":"https://github.com/huchenxucs/ChatDB","last_synced_at":"2025-05-09T22:31:19.869Z","repository":{"id":173727786,"uuid":"643449711","full_name":"huchenxucs/ChatDB","owner":"huchenxucs","description":"The official repository of \"ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory\".","archived":false,"fork":false,"pushed_at":"2023-06-19T20:09:52.000Z","size":378,"stargazers_count":534,"open_issues_count":11,"forks_count":46,"subscribers_count":15,"default_branch":"main","last_synced_at":"2024-11-16T06:31:52.314Z","etag":null,"topics":["database","large-language-models","memory","symbolic-execution"],"latest_commit_sha":null,"homepage":"https://chatdatabase.github.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/huchenxucs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-21T07:39:43.000Z","updated_at":"2024-11-07T10:28:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"cea37c38-0b0d-4621-8b1e-e4f02d5916b2","html_url":"https://github.com/huchenxucs/ChatDB","commit_stats":null,"previous_names":["huchenxucs/chatdb"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huchenxucs%2FChatDB","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huchenxucs%2FChatDB/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huchenxucs%2FChatDB/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huchenxucs%2FChatDB/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huchenxucs","download_url":"https://codeload.github.com/huchenxucs/ChatDB/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335590,"owners_count":21892703,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["database","large-language-models","memory","symbolic-execution"],"created_at":"2024-08-03T09:01:49.049Z","updated_at":"2025-05-09T22:31:19.863Z","avatar_url":"https://github.com/huchenxucs.png","language":"Python","funding_links":[],"categories":["A01_文本生成_文本对话","Python"],"sub_categories":["大语言对话模型及数据"],"readme":"# ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory\n\n### [Paper](https://arxiv.org/abs/2306.03901) | [Project Page](https://chatdatabase.github.io/)\n\nThis is the official repository of the paper: **ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory**.\n\n**We will continuously add new features to this code repository. Please stay tuned!**\n\n![teaser](assets/teaser.png)\n\nLarge language models (LLMs) with memory are computationally universal.\nHowever, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains.\nDue to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning.\nIn this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning.\nSuch a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases.\nWe validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning.\n\n## Quick Start\n### Install dependencies\n```bash\nconda create -n chatdb python=3.9\nconda activate chatdb\npip install -r requirements.txt\n```\n\n### Add keys\n```bash\ncp .env.template .env\n# add OPENAI_API_KEY and MYSQL_PASSWORD\n```\n\n### A minimal CLI demo in a fruit shop scenario\n```bash\npython chatdb.py\n```\nThe CLI demo looks as follows.\n![cli-demo](assets/cli_demo.jpeg)\n\n## Citation\nIf you find our work useful for your research, please consider citing the paper:\n```bash\n@misc{hu2023chatdb,\n      title={ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory},\n      author={Chenxu Hu and Jie Fu and Chenzhuang Du and Simian Luo and Junbo Zhao and Hang Zhao},\n      year={2023},\n      eprint={2306.03901},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuchenxucs%2FChatDB","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuchenxucs%2FChatDB","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuchenxucs%2FChatDB/lists"}