[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72634":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":36,"readmeContent":37,"aiSummary":38,"trendingCount":16,"starSnapshotCount":16,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},72634,"MindSearch","InternLM\u002FMindSearch","InternLM","🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)","",null,"JavaScript",6871,687,48,47,0,3,11,18,9,77.81,"Apache License 2.0",false,"main",[26,27,28,29,30,31,32,33,34,35],"ai-search-engine","gpt","llm","llms","multi-agent-systems","perplexity-ai","search","searchgpt","transformer","web-search","2026-06-12 04:01:06","\u003Cdiv id=\"top\">\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n\n\u003Cpicture>\n  \u003Csource srcset=\"assets\u002Flogo.svg\" media=\"(prefers-color-scheme: light)\">\n  \u003Csource srcset=\"assets\u002Flogo-darkmode.svg\" media=\"(prefers-color-scheme: dark)\">\n  \u003Cimg src=\"assets\u002Flogo.svg\" alt=\"Logo\" width=\"50%\">\n\u003C\u002Fpicture>\n\n[📃 Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.20183) | [💻 Demo](https:\u002F\u002Finternlm-chat.intern-ai.org.cn\u002F)\n\nEnglish | [简体中文](README_zh-CN.md)\n\n\u003Chttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F44ffe4b9-be26-4b93-a77b-02fed16e33fe>\n\n\u003C\u002Fdiv>\n\u003C\u002Fp>\n\n## ✨ MindSearch: Mimicking Human Minds Elicits Deep AI Searcher\n\n## 📅 Changelog\n\n- 2024\u002F11\u002F05: 🥳 MindSearch is now deployed on Puyu! 👉 [Try it](https:\u002F\u002Finternlm-chat.intern-ai.org.cn\u002F) 👈\n  -  Refactored the agent module based on [Lagent v0.5](https:\u002F\u002Fgithub.com\u002FInternLM\u002Flagent) for better performance in concurrency.\n  -  Improved the UI to embody the simultaneous multi-query search.\n\n\n## ⚽️ Build Your Own MindSearch\n\n### Step1: Dependencies Installation\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FInternLM\u002FMindSearch\ncd MindSearch\npip install -r requirements.txt\n```\n\n### Step2: Setup Environment Variables\n\nBefore setting up the API, you need to configure environment variables. Rename the `.env.example` file to `.env` and fill in the required values.\n\n```bash\nmv .env.example .env\n# Open .env and add your keys and model configurations\n```\n\n### Step3: Setup MindSearch API\n\nSetup FastAPI Server.\n\n```bash\npython -m mindsearch.app --lang en --model_format internlm_server --search_engine DuckDuckGoSearch --asy \n```\n\n- `--lang`: language of the model, `en` for English and `cn` for Chinese.\n- `--model_format`: format of the model.\n  - `internlm_server` for InternLM2.5-7b-chat with local server. (InternLM2.5-7b-chat has been better optimized for Chinese.)\n  - `gpt4` for GPT4.\n    if you want to use other models, please modify [models](.\u002Fmindsearch\u002Fagent\u002Fmodels.py)\n- `--search_engine`: Search engine.\n  - `DuckDuckGoSearch` for search engine for DuckDuckGo.\n  - `BingSearch` for Bing search engine.\n  - `BraveSearch` for Brave search web api engine.\n  - `GoogleSearch` for Google Serper web search api engine.\n  - `TencentSearch` for Tencent search api engine.\n  \n  Please set your Web Search engine API key as the `WEB_SEARCH_API_KEY` environment variable unless you are using `DuckDuckGo`, or `TencentSearch` that requires secret id as `TENCENT_SEARCH_SECRET_ID` and secret key as `TENCENT_SEARCH_SECRET_KEY`.\n- `--asy`: deploy asynchronous agents.\n\n### Step4: Setup MindSearch Frontend\n\nProviding following frontend interfaces,\n\n- React\n\nFirst configurate the backend URL for Vite proxy.\n\n```bash\nHOST=\"127.0.0.1\"  # modify as you need\nPORT=8002\nsed -i -r \"s\u002Ftarget:\\s*\\\"\\\"\u002Ftarget: \\\"${HOST}:${PORT}\\\"\u002F\" frontend\u002FReact\u002Fvite.config.ts\n```\n\n```bash\n# Install Node.js and npm\n# for Ubuntu\nsudo apt install nodejs npm\n\n# for windows\n# download from https:\u002F\u002Fnodejs.org\u002Fzh-cn\u002Fdownload\u002Fprebuilt-installer\n\n# Install dependencies\n\ncd frontend\u002FReact\nnpm install\nnpm start\n```\n\nDetails can be found in [React](.\u002Ffrontend\u002FReact\u002FREADME.md)\n\n- Gradio\n\n```bash\npython frontend\u002Fmindsearch_gradio.py\n```\n\n- Streamlit\n\n```bash\nstreamlit run frontend\u002Fmindsearch_streamlit.py\n```\n\n## 🌐 Change Web Search API\n\nTo use a different type of web search API, modify the `searcher_type` attribute in the `searcher_cfg` located in `mindsearch\u002Fagent\u002F__init__.py`. Currently supported web search APIs include:\n\n- `GoogleSearch`\n- `DuckDuckGoSearch`\n- `BraveSearch`\n- `BingSearch`\n- `TencentSearch`\n\nFor example, to change to the Brave Search API, you would configure it as follows:\n\n```python\nBingBrowser(\n    searcher_type='BraveSearch',\n    topk=2,\n    api_key=os.environ.get('BRAVE_API_KEY', 'YOUR BRAVE API')\n)\n```\n\n## 🐞 Using the Backend Without Frontend\n\nFor users who prefer to interact with the backend directly, use the `backend_example.py` script. This script demonstrates how to send a query to the backend and process the response.\n\n```bash\npython backend_example.py\n```\n\nMake sure you have set up the environment variables and the backend is running before executing the script.\n\n## 🐞 Debug Locally\n\n```bash\npython -m mindsearch.terminal\n```\n\n## 📝 License\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n## Citation\n\nIf you find this project useful in your research, please consider cite:\n\n```\n@article{chen2024mindsearch,\n  title={MindSearch: Mimicking Human Minds Elicits Deep AI Searcher},\n  author={Chen, Zehui and Liu, Kuikun and Wang, Qiuchen and Liu, Jiangning and Zhang, Wenwei and Chen, Kai and Zhao, Feng},\n  journal={arXiv preprint arXiv:2407.20183},\n  year={2024}\n}\n```\n\n## Our Projects\n\nExplore our additional research on large language models, focusing on LLM agents.\n\n- [Lagent](https:\u002F\u002Fgithub.com\u002FInternLM\u002Flagent): A lightweight framework for building LLM-based agents\n- [AgentFLAN](https:\u002F\u002Fgithub.com\u002FInternLM\u002FAgent-FLAN): An innovative approach for constructing and training with high-quality agent datasets (ACL 2024 Findings)\n- [T-Eval](https:\u002F\u002Fgithub.com\u002Fopen-compass\u002FT-Eval): A Fine-grained tool utilization evaluation benchmark (ACL 2024)\n","MindSearch 是一个基于大语言模型的多代理框架，用于构建类似Perplexity.ai Pro和SearchGPT的网络搜索引擎。其核心功能包括通过多代理系统模仿人类思维过程以实现深层次的信息检索，并支持多种搜索引擎如DuckDuckGo、Bing等。技术上，MindSearch采用了FastAPI搭建后端服务，前端则提供了React界面供用户交互；同时它还兼容InternLM2.5-7b-chat（特别优化了中文支持）及GPT4等多种模型格式。此项目适用于需要定制化智能搜索解决方案的情景，比如企业内部知识库查询或是特定领域信息挖掘等。",2,"2026-06-11 03:42:54","high_star"]