{"id":13456001,"url":"https://github.com/dataelement/bisheng","last_synced_at":"2026-01-28T15:08:04.790Z","repository":{"id":191162271,"uuid":"684031003","full_name":"dataelement/bisheng","owner":"dataelement","description":"BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.","archived":false,"fork":false,"pushed_at":"2025-04-29T12:32:27.000Z","size":48448,"stargazers_count":8276,"open_issues_count":95,"forks_count":1370,"subscribers_count":606,"default_branch":"main","last_synced_at":"2025-04-29T13:30:17.353Z","etag":null,"topics":["agent","ai","chatbot","enterprise","finetune","genai","gpt","langchian","llama","llm","llmdevops","llmops","ocr","openai","orchestration","python","rag","react","sft","workflow"],"latest_commit_sha":null,"homepage":"http://www.bisheng.ai","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dataelement.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-08-28T10:00:24.000Z","updated_at":"2025-04-29T08:55:50.000Z","dependencies_parsed_at":"2023-11-06T08:31:15.799Z","dependency_job_id":"692dfe65-8431-4bcb-931c-c798aa7d8db9","html_url":"https://github.com/dataelement/bisheng","commit_stats":{"total_commits":1875,"total_committers":34,"mean_commits":55.14705882352941,"dds":0.6554666666666666,"last_synced_commit":"bef1878c44cab34eb01493cece3d5d28d3f59f41"},"previous_names":["dataelement/bisheng"],"tags_count":65,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dataelement%2Fbisheng/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dataelement","download_url":"https://codeload.github.com/dataelement/bisheng/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252721033,"owners_count":21793746,"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":["agent","ai","chatbot","enterprise","finetune","genai","gpt","langchian","llama","llm","llmdevops","llmops","ocr","openai","orchestration","python","rag","react","sft","workflow"],"created_at":"2024-07-31T08:01:14.650Z","updated_at":"2026-01-28T15:08:04.784Z","avatar_url":"https://github.com/dataelement.png","language":"TypeScript","readme":"**Proudly made by Chinese，May we, like the creators of Deepseek and Black Myth: Wukong, bring more wonder and greatness to the world.**\n\n\u003e 源自中国匠心，希望我们能像 [Deepseek]、[黑神话：悟空] 团队一样，给世界带来更多美好。\n\n\u003cimg src=\"https://dataelem.com/bs/face.png\" alt=\"Bisheng banner\"\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://dataelem.feishu.cn/wiki/ZxW6wZyAJicX4WkG0NqcWsbynde\"\u003e\u003cimg src=\"https://img.shields.io/badge/docs-Wiki-brightgreen\"\u003e\u003c/a\u003e\n    \u003cimg src=\"https://img.shields.io/github/license/dataelement/bisheng\" alt=\"license\"/\u003e\n    \u003ca href=\"\"\u003e\u003cimg src=\"https://img.shields.io/github/last-commit/dataelement/bisheng\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://star-history.com/#dataelement/bisheng\u0026Timeline\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/dataelement/bisheng?color=yellow\"\u003e\u003c/a\u003e \n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"./README_CN.md\"\u003e简体中文\u003c/a\u003e |\n  \u003ca href=\"./README.md\"\u003eEnglish\u003c/a\u003e |\n  \u003ca href=\"./README_JPN.md\"\u003e日本語\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://trendshift.io/repositories/717\" target=\"_blank\"\u003e\u003cimg src=\"https://trendshift.io/api/badge/repositories/717\" alt=\"dataelement%2Fbisheng | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cdiv class=\"column\" align=\"middle\"\u003e\n  \u003c!-- \u003ca href=\"https://bisheng.slack.com/join/shared_invite/\"\u003e --\u003e\n    \u003c!-- \u003cimg src=\"https://img.shields.io/badge/Join-Slack-orange\" alt=\"join-slack\"/\u003e --\u003e\n  \u003c/a\u003e\n  \u003c!-- \u003cimg src=\"https://img.shields.io/github/license/bisheng-io/bisheng\" alt=\"license\"/\u003e --\u003e\n  \u003c!-- \u003cimg src=\"https://img.shields.io/docker/pulls/bisheng-io/bisheng\" alt=\"docker-pull-count\" /\u003e --\u003e\n\u003c/div\u003e\n\n\nBISHENG is an open LLM application devops platform, focusing on enterprise scenarios. It has been used by a large number of industry leading organizations and Fortune 500 companies.\n\n\"Bi Sheng\" was the inventor of movable type printing, which played a vital role in promoting the transmission of human knowledge. We hope that BISHENG can also provide strong support for the widespread implementation of intelligent applications. Everyone is welcome to participate.\n\n\n## Features \n1. **Lingsight, a general-purpose agent with expert-level taste**: Through the [AGL](https://github.com/dataelement/AgentGuidanceLanguage)(Agent Guidance Language) framework, we embed domain experts’ preferences, experience, and business logic into the AI, enabling the agent to exhibit “expert-level understanding” when handling tasks.  \n\u003cp align=\"center\"\u003e\u003cimg src=\"https://dataelem.com/bs/Linsight.png\" alt=\"sence1\"\u003e\u003c/p\u003e   \n\n2. **Unique [BISHENG Workflow](https://dataelem.feishu.cn/wiki/R7HZwH5ZGiJUDrkHZXicA9pInif)**\n   - 🧩 **Independent and comprehensive application orchestration framework**: Enables the execution of various tasks within a single framework (while similar products rely on bot invocation or separate chatflow and workflow modules for different tasks).\n   - 🔄 **Human in the loop**: Allows users to intervene and provide feedback during the execution of workflows (including multi-turn conversations), whereas similar products can only execute workflows from start to finish without intervention.\n   - 💥 **Powerful**: Supports loops, parallelism, batch processing, conditional logic, and free combination of all logic components. It also handles complex scenarios such as multi-type input/output, report generation, content review, and more.\n   - 🖐️ **User-friendly and intuitive**: Operations like loops, parallelism, and batch processing, which require specialized components in similar products, can be easily visualized in BISHENG as a \"flowchart\" (drawing a loop forms a loop, aligning elements creates parallelism, and selecting multiple items enables batch processing).\n   \u003cp align=\"center\"\u003e\u003cimg src=\"https://dataelem.com/bs/bisheng_workflow.png\" alt=\"sence0\"\u003e\u003c/p\u003e\n\n3. \u003cb\u003eDesigned for Enterprise Applications\u003c/b\u003e: Document review, fixed-layout report generation, multi-agent collaboration, policy update comparison, support ticket assistance, customer service assistance, meeting minutes generation, resume screening, call record analysis, unstructured data governance, knowledge mining, data analysis, and more.   \nThe platform supports the construction of \u003cb\u003ehighly complex enterprise application scenarios\u003c/b\u003e and offers \u003cb\u003edeep optimization\u003c/b\u003e \twith hundreds of components and thousands of parameters.\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://dataelem.com/bs/chat.png\" alt=\"sence1\"\u003e\u003c/p\u003e\n\n4. \u003cb\u003eEnterprise-grade\u003c/b\u003e features are the fundamental guarantee for application implementation: security review, RBAC, user group management, traffic control by group, SSO/LDAP, vulnerability scanning and patching, high availability deployment solutions, monitoring, statistics, and more.\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://dataelem.com/bs/pro.png\" alt=\"sence2\"\u003e\u003c/p\u003e\n\n5. \u003cb\u003eHigh-Precision Document Parsing\u003c/b\u003e: Our high-precision document parsing model is trained on a vast amount of high-quality data accumulated over past 5 years. It includes high-precision printed text, handwritten text, and rare character recognition models, table recognition models, layout analysis models, and seal models., table recognition models, layout analysis models, and seal models. You can deploy it privately for free.\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://dataelem.com/bs/ocr.png\" alt=\"sence3\"\u003e\u003c/p\u003e\n\n6. A community for sharing best practices across various enterprise scenarios: An open repository of application cases and best practices.\n## Quick start \n\nPlease ensure the following conditions are met before installing BISHENG:\n- CPU \u003e= 4 Virtual Cores\n- RAM \u003e= 16 GB\n- Docker 19.03.9+\n- Docker Compose 1.25.1+\n\u003e Recommended hardware condition: 18 virtual cores, 48G. In addition to installing BISHENG, we will also install the following third-party components by default: ES, Milvus, and Onlyoffice.\n\nDownload BISHENG\n```bash\ngit clone https://github.com/dataelement/bisheng.git\n# Enter the installation directory\ncd bisheng/docker\n\n# If the system does not have the git command, you can download the BISHENG code as a zip file.\nwget https://github.com/dataelement/bisheng/archive/refs/heads/main.zip\n# Unzip and enter the installation directory\nunzip main.zip \u0026\u0026 cd bisheng-main/docker\n```\nStart BISHENG\n```bash\ndocker compose -f docker-compose.yml -p bisheng up -d\n```\nAfter the startup is complete, access http://IP:3001 in the browser. The login page will appear, proceed with user registration. \n\nBy default, the first registered user will become the system admin. \n\nFor more installation and deployment issues, refer to:：[Self-hosting](https://dataelem.feishu.cn/wiki/BSCcwKd4Yiot3IkOEC8cxGW7nPc)\n\n## Acknowledgement \nThis repo benefits from [langchain](https://github.com/langchain-ai/langchain) [langflow](https://github.com/logspace-ai/langflow) [unstructured](https://github.com/Unstructured-IO/unstructured) and [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) . Thanks for their wonderful works.\n\n\u003cb\u003eThank you to our contributors：\u003c/b\u003e\n\n\u003ca href=\"https://github.com/dataelement/bisheng/graphs/contributors\"\u003e\n  \u003cimg src=\"https://contrib.rocks/image?repo=dataelement/bisheng\" /\u003e\n\u003c/a\u003e\n\n\n\n## Community \u0026 contact \nWelcome to join our discussion group\n\n\u003cimg src=\"https://www.dataelem.com/nstatic/qrcode.png\" alt=\"Wechat QR Code\"\u003e\n\n\n\u003c!--\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=dataelement/bisheng\u0026type=Date)](https://star-history.com/#dataelement/bisheng\u0026Date)\n--\u003e\n","funding_links":[],"categories":["Project List","A01_文本生成_文本对话","TypeScript","Python","Chatbots","Building","Deployment and Serving","Repos","Agent Frameworks (fully local) (25)","AI Agent Frameworks \u0026 SDKs","Agents 开发平台"],"sub_categories":["\u003cspan id=\"tool\"\u003eLLM (LLM \u0026 Tool)\u003c/span\u003e","大语言对话模型及数据","LLM Models","Orchestration Frameworks"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataelement%2Fbisheng","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdataelement%2Fbisheng","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdataelement%2Fbisheng/lists"}