[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72101":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":39,"readmeContent":40,"aiSummary":41,"trendingCount":16,"starSnapshotCount":16,"syncStatus":42,"lastSyncTime":43,"discoverSource":44},72101,"ai-data-science-team","business-science\u002Fai-data-science-team","business-science","An AI-powered data science team of agents to help you perform common data science tasks 10X faster.","",null,"Python",5283,918,89,25,0,6,53,68,18,103.69,"MIT License",false,"master",[26,27,28,29,30,31,32,33,34,35,36,37,38],"agents","ai","ai-engineer","ai-engineering","copilot","data-science","data-scientist","generative-ai","gpt","machine-learning","ml-engineer","ml-engineering","openai","2026-06-12 04:01:03","\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbusiness-science\u002Fai-data-science-team\">\n    \u003Cpicture>\n      \u003Cimg src=\".\u002Fimg\u002Fai_data_science_logo.png\" alt=\"AI Data Science Team\" width=\"360\">\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n  \u003Cem>AI Data Science Team + AI Pipeline Studio\u003C\u002Fem>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.python.org\u002Fpypi\u002Fai-data-science-team\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fai-data-science-team.svg?style=for-the-badge\" alt=\"PyPI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbusiness-science\u002Fai-data-science-team\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fai-data-science-team.svg?style=for-the-badge\" alt=\"versions\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbusiness-science\u002Fai-data-science-team\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fbusiness-science\u002Fai-data-science-team.svg?style=for-the-badge\" alt=\"license\">\u003C\u002Fa>\n  \u003Cimg alt=\"GitHub Repo stars\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbusiness-science\u002Fai-data-science-team?style=for-the-badge\">\n\u003C\u002Fdiv>\n\n# AI Data Science Team\n\nAI Data Science Team is a Python library of specialized agents for common data science workflows, plus a flagship app: **AI Pipeline Studio**. The Studio turns your work into a visual, reproducible pipeline, while the AI team handles data loading, cleaning, visualization, and modeling.\n\n**Status:** Beta. Breaking changes may occur until 0.1.0.\n\n[**Please ⭐ us on GitHub (it takes 2 seconds and means a lot).**](https:\u002F\u002Fgithub.com\u002Fbusiness-science\u002Fai-data-science-team)\n\n## AI Pipeline Studio (Flagship App)\n\nAI Pipeline Studio is the main example of the AI Data Science Team in action.\n\n![AI Pipeline Studio](\u002Fimg\u002Fapps\u002Fai_pipeline_studio_app.jpg)\n\nHighlights:\n- Pipeline-first workspace: Visual Editor, Table, Chart, EDA, Code, Model, Predictions, MLflow\n- Manual + AI steps with lineage and reproducible scripts\n- Multi-dataset handling and merge workflows\n- Project saves: metadata-only or full-data\n- Storage footprint controls and rehydrate workflows\n\nRun it:\n```bash\nstreamlit run apps\u002Fai-pipeline-studio-app\u002Fapp.py\n```\n\nFull app docs: `apps\u002Fai-pipeline-studio-app\u002FREADME.md`\n\n## Quickstart\n\n### Requirements\n- Python 3.10+\n- OpenAI API key (or Ollama for local models)\n\n### Install the app and library\nClone the repo and install in editable mode:\n```bash\npip install -e .\n```\n\n### Run the AI Pipeline Studio app\n```bash\nstreamlit run apps\u002Fai-pipeline-studio-app\u002Fapp.py\n```\n\n## Library Overview\n\nThe repository includes both the **AI Pipeline Studio** app and the underlying **AI Data Science Team** library. The library provides agent building blocks and multi-agent workflows for:\n- Data loading and inspection\n- Cleaning, wrangling, and feature engineering\n- Visualization and EDA\n- Modeling and evaluation (H2O + MLflow tools)\n- SQL database interaction\n\n### Agents (Snapshot)\n\nAgent examples live in `examples\u002F`. Notable agents:\n- Data Loader Tools Agent\n- Data Wrangling Agent\n- Data Cleaning Agent\n- Data Visualization Agent\n- EDA Tools Agent\n- Feature Engineering Agent\n- SQL Database Agent\n- H2O ML Agent\n- MLflow Tools Agent\n- Multi-agent workflows (e.g., Pandas Data Analyst, SQL Data Analyst)\n- Supervisor Agent (oversees other agents)\n- Custom tools for data science tasks\n\n## Apps\n\nSee all apps in `apps\u002F`. Notable apps:\n- AI Pipeline Studio: `apps\u002Fai-pipeline-studio-app\u002F`\n- EDA Explorer App: `apps\u002Fexploratory-copilot-app\u002F`\n- Pandas Data Analyst App: `apps\u002Fpandas-data-analyst-app\u002F`\n\n## Use OpenAI\n\n```python\nfrom langchain_openai import ChatOpenAI\nllm = ChatOpenAI(\n    model_name=\"gpt-4.1-mini\",\n)\n```\n\n## Use Ollama (Local LLM)\n\n```bash\nollama serve\nollama pull llama3.1:8b\n```\n\n```python\nfrom langchain_ollama import ChatOllama\n\nllm = ChatOllama(\n    model=\"llama3.1:8b\",\n)\n```\n\n## Next-Gen AI Agentic Workshop\n\nWant to learn how to build AI agents and AI apps for real data science workflows? Join my next‑gen AI workshop:\nhttps:\u002F\u002Flearn.business-science.io\u002Fai-register\n","AI Data Science Team 是一个基于Python的库，它提供了一组专门用于常见数据科学工作流程的智能代理，以及一个名为AI Pipeline Studio的核心应用程序。该项目通过集成多种功能如数据加载、清洗、可视化及建模等，极大地加速了数据科学家的工作效率。其技术亮点在于结合了人工与AI操作步骤，并支持多数据集处理和合并工作流，同时保证所有步骤具有可追溯性和脚本可复现性。非常适合需要快速构建数据科学项目或希望提高现有数据分析流程效率的场景使用。",2,"2026-06-11 03:40:21","high_star"]