{"id":31963,"date":"2025-07-01T02:27:10","date_gmt":"2025-06-30T18:27:10","guid":{"rendered":"https:\/\/www.kdjingpai.com\/?p=31963"},"modified":"2025-07-01T02:34:11","modified_gmt":"2025-06-30T18:34:11","slug":"deerflow","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/en\/deerflow\/","title":{"rendered":"DeerFlow\uff1a\u5f00\u6e90\u7684\u6df1\u5ea6\u7814\u7a76\u81ea\u52a8\u5316\u6846\u67b6"},"content":{"rendered":"<p>DeerFlow \u662f\u7531\u5b57\u8282\u8df3\u52a8\u5f00\u6e90\u7684\u4e00\u4e2a\u6df1\u5ea6\u7814\u7a76\u6846\u67b6\uff0c\u65e8\u5728\u901a\u8fc7\u591a\u667a\u80fd\u4f53\u534f\u4f5c\u5b9e\u73b0\u7814\u7a76\u4efb\u52a1\u7684\u81ea\u52a8\u5316\u3002\u5b83\u7ed3\u5408\u4e86\u8bed\u8a00\u6a21\u578b\u548c\u4e13\u4e1a\u5de5\u5177\uff0c\u5982\u7f51\u9875\u641c\u7d22\u3001\u7f51\u9875\u722c\u866b\u548c Python \u4ee3\u7801\u6267\u884c\uff0c\u5e2e\u52a9\u7528\u6237\u9ad8\u6548\u5b8c\u6210\u590d\u6742\u7684\u7814\u7a76\u4efb\u52a1\u3002DeerFlow \u57fa\u4e8e LangChain \u548c <a href=\"https:\/\/www.kdjingpai.com\/langgraph\/\">LangGraph<\/a> \u6784\u5efa\uff0c\u91c7\u7528\u6a21\u5757\u5316\u8bbe\u8ba1\uff0c\u652f\u6301\u7075\u6d3b\u7684\u4efb\u52a1\u5206\u914d\u548c\u72b6\u6001\u7ba1\u7406\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u7b80\u5355\u7684\u914d\u7f6e\u5feb\u901f\u90e8\u7f72\uff0c\u9002\u5408\u7814\u7a76\u4eba\u5458\u3001\u5f00\u53d1\u8005\u6216\u9700\u8981\u5904\u7406\u5927\u91cf\u4fe1\u606f\u7684\u7528\u6237\u3002\u9879\u76ee\u5b8c\u5168\u5f00\u6e90\uff0c\u9075\u5faa MIT \u8bb8\u53ef\u8bc1\uff0c\u4efb\u4f55\u4eba\u90fd\u53ef\u4ee5\u5728 GitHub \u4e0a\u83b7\u53d6\u6e90\u4ee3\u7801\u5e76\u8d21\u732e\u4ee3\u7801\u3002DeerFlow \u63d0\u4f9b\u76f4\u89c2\u7684\u5728\u7ebf\u4f53\u9a8c\uff0c\u652f\u6301\u4e00\u952e\u90e8\u7f72\u5230 Volcengine \u4e91\u5e73\u53f0\uff0c\u65b9\u4fbf\u7528\u6237\u5feb\u901f\u4e0a\u624b\u3002<\/p>\n<p><img decoding=\"async\" title=\"DeerFlow\uff1a\u5f00\u6e90\u7684\u6df1\u5ea6\u7814\u7a76\u81ea\u52a8\u5316\u6846\u67b6-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/07\/38ab1dd76cfb81e.jpg\" alt=\"DeerFlow\uff1a\u5f00\u6e90\u7684\u6df1\u5ea6\u7814\u7a76\u81ea\u52a8\u5316\u6846\u67b6-1\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u591a\u667a\u80fd\u4f53\u534f\u4f5c<\/strong>\uff1a\u901a\u8fc7 Researcher\u3001Coder \u548c Reporter \u7b49\u667a\u80fd\u4f53\u6a21\u5757\uff0c\u5206\u5de5\u5904\u7406\u641c\u7d22\u3001\u4ee3\u7801\u5206\u6790\u548c\u62a5\u544a\u751f\u6210\u4efb\u52a1\u3002<\/li>\n<li><strong>\u7f51\u9875\u641c\u7d22\u4e0e\u722c\u53d6<\/strong>\uff1a\u96c6\u6210 <a href=\"https:\/\/www.kdjingpai.com\/tavily\/\">Tavily<\/a> \u548c Brave \u641c\u7d22\uff0c\u652f\u6301\u9ad8\u6548\u7684\u4fe1\u606f\u6536\u96c6\u548c\u7f51\u9875\u5185\u5bb9\u63d0\u53d6\u3002<\/li>\n<li><strong>Python \u4ee3\u7801\u6267\u884c<\/strong>\uff1a\u5185\u7f6e Python REPL \u5de5\u5177\uff0c\u5141\u8bb8\u7528\u6237\u76f4\u63a5\u8fd0\u884c\u548c\u5206\u6790\u4ee3\u7801\u3002<\/li>\n<li><strong>\u6587\u672c\u8f6c\u8bed\u97f3<\/strong>\uff1a\u901a\u8fc7 Volcengine TTS API\uff0c\u5c06\u7814\u7a76\u62a5\u544a\u8f6c\u4e3a\u9ad8\u8d28\u91cf\u97f3\u9891\uff0c\u652f\u6301\u8bed\u901f\u3001\u97f3\u91cf\u548c\u97f3\u8c03\u8c03\u6574\u3002<\/li>\n<li><strong>\u62a5\u544a\u751f\u6210<\/strong>\uff1a\u81ea\u52a8\u751f\u6210\u7ed3\u6784\u5316\u7684\u7814\u7a76\u62a5\u544a\uff0c\u652f\u6301\u5bfc\u51fa\u4e3a\u6587\u6863\u6216 PPT \u683c\u5f0f\u3002<\/li>\n<li><strong>\u4e00\u952e\u90e8\u7f72<\/strong>\uff1a\u652f\u6301\u5728 Volcengine \u4e91\u5e73\u53f0\u4e0a\u5feb\u901f\u90e8\u7f72\uff0c\u7b80\u5316\u73af\u5883\u914d\u7f6e\u3002<\/li>\n<li><strong>\u4ea4\u4e92\u6a21\u5f0f<\/strong>\uff1a\u63d0\u4f9b\u547d\u4ee4\u884c\u4ea4\u4e92\u6a21\u5f0f\uff0c\u5141\u8bb8\u7528\u6237\u52a8\u6001\u8c03\u6574\u7814\u7a76\u8ba1\u5212\u3002<\/li>\n<li><strong>\u5f00\u6e90\u8d21\u732e<\/strong>\uff1a\u57fa\u4e8e MIT \u8bb8\u53ef\u8bc1\uff0c\u9f13\u52b1\u793e\u533a\u53c2\u4e0e\u5f00\u53d1\u548c\u4f18\u5316\u3002<\/li>\n<\/ul>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<p>DeerFlow \u7684\u5b89\u88c5\u548c\u914d\u7f6e\u8fc7\u7a0b\u7b80\u5355\uff0c\u9002\u5408\u6709\u57fa\u7840\u7f16\u7a0b\u7ecf\u9a8c\u7684\u7528\u6237\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u7684\u5b89\u88c5\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li><strong>\u514b\u9686\u4ed3\u5e93<\/strong><br \/>\n\u5728\u7ec8\u7aef\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\uff0c\u514b\u9686 DeerFlow \u4ed3\u5e93\u5230\u672c\u5730\uff1a<\/p>\n<pre><code>git clone https:\/\/github.com\/bytedance\/deer-flow.git\r\ncd deer-flow\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u5b89\u88c5\u4f9d\u8d56<\/strong><br \/>\n\u4f7f\u7528\u00a0<code>uv<\/code>\u00a0\u5de5\u5177\u81ea\u52a8\u521b\u5efa Python \u865a\u62df\u73af\u5883\u5e76\u5b89\u88c5\u6240\u9700\u4f9d\u8d56\uff1a<\/p>\n<pre><code>uv <a href=\"https:\/\/www.kdjingpai.com\/sync\/\">sync<\/a>\r\n<\/code><\/pre>\n<p>\u6ce8\u610f\uff1a\u786e\u4fdd\u5df2\u5b89\u88c5\u00a0<code>uv<\/code>\uff0c\u53ef\u901a\u8fc7\u00a0<code>pip install uv<\/code>\u00a0\u5b89\u88c5\u3002<\/li>\n<li><strong>\u914d\u7f6e\u73af\u5883\u53d8\u91cf<\/strong><br \/>\n\u590d\u5236\u793a\u4f8b\u914d\u7f6e\u6587\u4ef6\u5e76\u586b\u5199 API \u5bc6\u94a5\uff1a<\/p>\n<pre><code>cp .env.example .env\r\n<\/code><\/pre>\n<p>\u5728\u00a0<code>.env<\/code>\u00a0\u6587\u4ef6\u4e2d\u6dfb\u52a0\u4ee5\u4e0b API \u5bc6\u94a5\uff1a<\/p>\n<ul>\n<li>Tavily API\uff1a\u7528\u4e8e\u7f51\u9875\u641c\u7d22\uff0c\u9700\u5728\u00a0<a href=\"https:\/\/app.tavily.com\/home\">Tavily \u5b98\u7f51<\/a>\u00a0\u6ce8\u518c\u83b7\u53d6\u3002<\/li>\n<li>Brave Search API\uff1a\u7528\u4e8e\u589e\u5f3a\u641c\u7d22\u529f\u80fd\uff0c\u9700\u5728\u00a0<a href=\"https:\/\/brave.com\/search\/api\/\">Brave Search<\/a>\u00a0\u6ce8\u518c\u3002<\/li>\n<li>Volcengine TTS API\uff1a\u7528\u4e8e\u6587\u672c\u8f6c\u8bed\u97f3\u529f\u80fd\uff0c\u9700\u5728 Volcengine \u5e73\u53f0\u83b7\u53d6\u51ed\u8bc1\u3002<br \/>\n\u793a\u4f8b\u00a0<code>.env<\/code>\u00a0\u6587\u4ef6\u5185\u5bb9\uff1a<\/li>\n<\/ul>\n<pre><code>TAVILY_API_KEY=your_tavily_api_key\r\nBRAVE_SEARCH_API_KEY=your_brave_api_key\r\nVOLCENGINE_TTS_KEY=your_volcengine_tts_key\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u914d\u7f6e\u6a21\u578b\u548c\u53c2\u6570<\/strong><br \/>\n\u590d\u5236\u793a\u4f8b\u914d\u7f6e\u6587\u4ef6\u5e76\u6839\u636e\u9700\u8981\u8c03\u6574\uff1a<\/p>\n<pre><code>cp conf.yaml.example conf.yaml\r\n<\/code><\/pre>\n<p>\u5728\u00a0<code>conf.yaml<\/code>\u00a0\u4e2d\u914d\u7f6e\u8bed\u8a00\u6a21\u578b\uff08\u5982 GPT \u6216\u5176\u4ed6\u652f\u6301\u7684\u6a21\u578b\uff09\u548c API \u5bc6\u94a5\u3002\u5177\u4f53\u914d\u7f6e\u53c2\u8003\u00a0<code>docs\/configuration_guide.md<\/code>\u3002<\/li>\n<li><strong>\u5b89\u88c5 Marp\uff08\u53ef\u9009\uff09<\/strong><br \/>\n\u5982\u679c\u9700\u8981\u751f\u6210 PPT \u683c\u5f0f\u7684\u62a5\u544a\uff0c\u9700\u5b89\u88c5 Marp CLI\uff1a<\/p>\n<pre><code>brew install marp-cli\r\n<\/code><\/pre>\n<p>\u5bf9\u4e8e\u975e macOS \u7cfb\u7edf\uff0c\u8bf7\u53c2\u8003\u00a0<a href=\"https:\/\/github.com\/marp-team\/marp-cli\">Marp CLI \u5b98\u7f51<\/a>\u00a0\u83b7\u53d6\u5b89\u88c5\u65b9\u6cd5\u3002<\/li>\n<li><strong>\u8fd0\u884c DeerFlow<\/strong><br \/>\n\u914d\u7f6e\u5b8c\u6210\u540e\uff0c\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u542f\u52a8\uff1a<\/p>\n<pre><code>python main.py --query \"\u4f60\u7684\u7814\u7a76\u95ee\u9898\" --interactive\r\n<\/code><\/pre>\n<p>\u4f8b\u5982\uff1a<\/p>\n<pre><code>python main.py --query \"\u91cf\u5b50\u8ba1\u7b97\u5bf9\u5bc6\u7801\u5b66\u7684\u5f71\u54cd\" --interactive\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u4e3b\u8981\u529f\u80fd<\/h3>\n<p>DeerFlow \u7684\u6838\u5fc3\u529f\u80fd\u56f4\u7ed5\u591a\u667a\u80fd\u4f53\u534f\u4f5c\uff0c\u5206\u4e3a\u4ee5\u4e0b\u51e0\u4e2a\u6a21\u5757\u7684\u64cd\u4f5c\u6d41\u7a0b\uff1a<\/p>\n<ol>\n<li><strong>\u7814\u7a76\u4efb\u52a1\u8f93\u5165<\/strong><br \/>\n\u7528\u6237\u901a\u8fc7\u547d\u4ee4\u884c\u8f93\u5165\u7814\u7a76\u95ee\u9898\uff0c\u4f8b\u5982\u201c\u5206\u6790\u91cf\u5b50\u8ba1\u7b97\u5bf9\u5bc6\u7801\u5b66\u7684\u5f71\u54cd\u201d\u3002DeerFlow \u7684 Planner \u667a\u80fd\u4f53\u4f1a\u5206\u89e3\u4efb\u52a1\uff0c\u751f\u6210\u7814\u7a76\u8ba1\u5212\uff0c\u5e76\u5206\u914d\u7ed9\u5408\u9002\u7684\u667a\u80fd\u4f53\u3002\u7528\u6237\u53ef\u5728\u4ea4\u4e92\u6a21\u5f0f\u4e0b\u52a8\u6001\u8c03\u6574\u8ba1\u5212\uff1a<\/p>\n<pre><code>python main.py --query \"\u4f60\u7684\u7814\u7a76\u95ee\u9898\" --interactive\r\n<\/code><\/pre>\n<p>\u4ea4\u4e92\u6a21\u5f0f\u4f1a\u63d0\u793a\u7528\u6237\u8f93\u5165\u989d\u5916\u4fe1\u606f\u6216\u786e\u8ba4\u8ba1\u5212\u3002<\/li>\n<li><strong>\u7f51\u9875\u641c\u7d22\u4e0e\u4fe1\u606f\u6536\u96c6<\/strong><br \/>\nResearcher \u667a\u80fd\u4f53\u4f7f\u7528 Tavily \u6216 Brave \u641c\u7d22 API \u6536\u96c6\u76f8\u5173\u4fe1\u606f\u3002\u5b83\u4f1a\u81ea\u52a8\u722c\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u63d0\u53d6\u5173\u952e\u6570\u636e\uff0c\u5e76\u5b58\u50a8\u5230\u4e34\u65f6\u6570\u636e\u5e93\u3002\u7528\u6237\u53ef\u901a\u8fc7\u914d\u7f6e\u6587\u4ef6\u8c03\u6574\u641c\u7d22\u6df1\u5ea6\uff1a<\/p>\n<pre><code>search:\r\nengine: tavily\r\nmax_results: 10\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4ee3\u7801\u6267\u884c\u4e0e\u5206\u6790<\/strong><br \/>\nCoder \u667a\u80fd\u4f53\u652f\u6301\u8fd0\u884c Python \u4ee3\u7801\u3002\u4f8b\u5982\uff0c\u7528\u6237\u8f93\u5165\u4e00\u4e2a\u6570\u636e\u5206\u6790\u4efb\u52a1\uff0cCoder \u4f1a\u751f\u6210\u5e76\u6267\u884c\u4ee3\u7801\uff1a<\/p>\n<pre><code>import pandas as pd\r\ndf = pd.read_csv('data.csv')\r\nprint(df.describe())\r\n<\/code><\/pre>\n<p>\u8fd0\u884c\u7ed3\u679c\u4f1a\u53cd\u9988\u5230\u7814\u7a76\u62a5\u544a\u4e2d\u3002\u7528\u6237\u53ef\u5728\u4ea4\u4e92\u6a21\u5f0f\u4e2d\u68c0\u67e5\u4ee3\u7801\u6267\u884c\u7ed3\u679c\u3002<\/li>\n<li><strong>\u62a5\u544a\u751f\u6210\u4e0e\u6587\u672c\u8f6c\u8bed\u97f3<\/strong><br \/>\nReporter \u667a\u80fd\u4f53\u5c06\u6536\u96c6\u7684\u4fe1\u606f\u6574\u7406\u4e3a\u7ed3\u6784\u5316\u62a5\u544a\uff0c\u652f\u6301\u5bfc\u51fa\u4e3a Markdown\u3001PDF \u6216 PPT \u683c\u5f0f\u3002\u7528\u6237\u53ef\u542f\u7528\u6587\u672c\u8f6c\u8bed\u97f3\u529f\u80fd\uff0c\u5c06\u62a5\u544a\u8f6c\u4e3a\u97f3\u9891\uff1a<\/p>\n<pre><code>python main.py --query \"\u4f60\u7684\u7814\u7a76\u95ee\u9898\" --tts\r\n<\/code><\/pre>\n<p>\u97f3\u9891\u6587\u4ef6\u4f1a\u4fdd\u5b58\u5230\u6307\u5b9a\u76ee\u5f55\uff0c\u652f\u6301\u8c03\u6574\u8bed\u901f\u548c\u97f3\u8c03\uff1a<\/p>\n<pre><code>tts:\r\nspeed: 1.0\r\nvolume: 1.0\r\n<a href=\"https:\/\/www.kdjingpai.com\/pitch\/\">pitch<\/a>: 0.0\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u81ea\u5b9a\u4e49\u5de5\u4f5c\u6d41<\/strong><br \/>\nDeerFlow \u4f7f\u7528 LangGraph \u7ba1\u7406\u667a\u80fd\u4f53\u72b6\u6001\uff0c\u7528\u6237\u53ef\u901a\u8fc7\u4fee\u6539\u00a0<code>conf.yaml<\/code>\u00a0\u81ea\u5b9a\u4e49\u4efb\u52a1\u6d41\u7a0b\u3002\u4f8b\u5982\uff0c\u589e\u52a0\u641c\u7d22\u8fed\u4ee3\u6b21\u6570\uff1a<\/p>\n<pre><code>max_plan_iterations: 3\r\nmax_step_num: 5\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h3>\u7279\u8272\u529f\u80fd\u64cd\u4f5c<\/h3>\n<ul>\n<li><strong>\u52a8\u6001\u4efb\u52a1\u8fed\u4ee3<\/strong>\uff1aPlanner \u667a\u80fd\u4f53\u652f\u6301\u6839\u636e\u641c\u7d22\u7ed3\u679c\u52a8\u6001\u8c03\u6574\u7814\u7a76\u8ba1\u5212\u3002\u4f8b\u5982\uff0c\u5982\u679c\u521d\u59cb\u641c\u7d22\u7ed3\u679c\u4e0d\u8db3\uff0cPlanner \u4f1a\u81ea\u52a8\u53d1\u8d77\u65b0\u4e00\u8f6e\u641c\u7d22\u3002<\/li>\n<li><strong>\u64ad\u5ba2\u751f\u6210<\/strong>\uff1a\u7ed3\u5408\u6587\u672c\u8f6c\u8bed\u97f3\u529f\u80fd\uff0cDeerFlow \u53ef\u5c06\u62a5\u544a\u8f6c\u4e3a\u64ad\u5ba2\u683c\u5f0f\uff0c\u9002\u5408\u5206\u4eab\u7814\u7a76\u6210\u679c\u3002<\/li>\n<li><strong>PPT \u751f\u6210<\/strong>\uff1a\u901a\u8fc7 Marp CLI\uff0cDeerFlow \u53ef\u5c06\u62a5\u544a\u8f6c\u4e3a\u4e13\u4e1a PPT\uff0c\u9002\u5408\u5b66\u672f\u4f1a\u8bae\u6216\u56e2\u961f\u6c47\u62a5\u3002<\/li>\n<\/ul>\n<h3>\u6ce8\u610f\u4e8b\u9879<\/h3>\n<ul>\n<li>\u786e\u4fdd\u7f51\u7edc\u8fde\u63a5\u7a33\u5b9a\uff0c\u4ee5\u652f\u6301 API \u8c03\u7528\u548c\u7f51\u9875\u722c\u53d6\u3002<\/li>\n<li>\u68c0\u67e5\u00a0<code>.env<\/code>\u00a0\u548c\u00a0<code>conf.yaml<\/code>\u00a0\u914d\u7f6e\uff0c\u907f\u514d\u56e0\u5bc6\u94a5\u9519\u8bef\u5bfc\u81f4\u529f\u80fd\u4e0d\u53ef\u7528\u3002<\/li>\n<li>\u53c2\u8003\u00a0<code>docs\/FAQ.md<\/code>\u00a0\u89e3\u51b3\u5e38\u89c1\u95ee\u9898\uff0c\u5982\u4f9d\u8d56\u5b89\u88c5\u5931\u8d25\u6216 API \u8bbf\u95ee\u9650\u5236\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u5e94\u7528\u573a\u666f<\/h2>\n<ol>\n<li><strong>\u5b66\u672f\u7814\u7a76<\/strong><br \/>\n\u5b66\u751f\u6216\u7814\u7a76\u4eba\u5458\u53ef\u4f7f\u7528 DeerFlow \u5feb\u901f\u6536\u96c6\u6587\u732e\u3001\u5206\u6790\u6570\u636e\u5e76\u751f\u6210\u7ed3\u6784\u5316\u62a5\u544a\u3002\u4f8b\u5982\uff0c\u8f93\u5165\u201c\u6700\u65b0\u7684\u4eba\u5de5\u667a\u80fd\u7b97\u6cd5\u7efc\u8ff0\u201d\uff0cDeerFlow \u4f1a\u81ea\u52a8\u641c\u7d22\u76f8\u5173\u8bba\u6587\u3001\u63d0\u53d6\u5173\u952e\u4fe1\u606f\u5e76\u751f\u6210\u62a5\u544a\u3002<\/li>\n<li><strong>\u6280\u672f\u5f00\u53d1<\/strong><br \/>\n\u5f00\u53d1\u8005\u53ef\u5229\u7528 Coder \u667a\u80fd\u4f53\u5206\u6790\u4ee3\u7801\u5e93\u6216\u8fd0\u884c\u5b9e\u9a8c\u4ee3\u7801\u3002\u4f8b\u5982\uff0c\u8f93\u5165\u201c\u6bd4\u8f83\u4e0d\u540c\u673a\u5668\u5b66\u4e60\u6a21\u578b\u7684\u6027\u80fd\u201d\uff0cDeerFlow \u4f1a\u6267\u884c Python \u811a\u672c\u5e76\u751f\u6210\u6bd4\u8f83\u62a5\u544a\u3002<\/li>\n<li><strong>\u5e02\u573a\u5206\u6790<\/strong><br \/>\n\u8425\u9500\u56e2\u961f\u53ef\u4f7f\u7528 DeerFlow \u6536\u96c6\u884c\u4e1a\u8d8b\u52bf\u6570\u636e\uff0c\u751f\u6210\u5e02\u573a\u62a5\u544a\u6216\u64ad\u5ba2\u3002\u4f8b\u5982\uff0c\u8f93\u5165\u201c2025\u5e74\u793e\u4ea4\u5a92\u4f53\u8d8b\u52bf\u201d\uff0cDeerFlow \u4f1a\u722c\u53d6\u76f8\u5173\u7f51\u9875\u5e76\u751f\u6210\u5206\u6790\u62a5\u544a\u3002<\/li>\n<li><strong>\u6559\u80b2\u57f9\u8bad<\/strong><br \/>\n\u6559\u5e08\u53ef\u4f7f\u7528 DeerFlow \u751f\u6210\u6559\u5b66\u6750\u6599\u6216 PPT\u3002\u4f8b\u5982\uff0c\u8f93\u5165\u201c\u91cf\u5b50\u8ba1\u7b97\u5165\u95e8\u201d\uff0cDeerFlow \u4f1a\u6574\u7406\u76f8\u5173\u5185\u5bb9\u5e76\u751f\u6210\u6559\u5b66\u5e7b\u706f\u7247\u3002<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n<h2>QA<\/h2>\n<ol>\n<li><strong>DeerFlow \u652f\u6301\u54ea\u4e9b\u8bed\u8a00\u6a21\u578b\uff1f<\/strong><br \/>\nDeerFlow \u652f\u6301\u591a\u79cd\u8bed\u8a00\u6a21\u578b\uff0c\u5305\u62ec GPT \u7cfb\u5217\u548c\u5176\u4ed6\u5f00\u6e90\u6a21\u578b\u3002\u7528\u6237\u53ef\u5728\u00a0<code>conf.yaml<\/code>\u00a0\u4e2d\u914d\u7f6e\u6a21\u578b\u7c7b\u578b\u548c API \u5bc6\u94a5\u3002<\/li>\n<li><strong>\u5982\u4f55\u89e3\u51b3 API \u5bc6\u94a5\u65e0\u6548\u7684\u95ee\u9898\uff1f<\/strong><br \/>\n\u68c0\u67e5\u00a0<code>.env<\/code>\u00a0\u6587\u4ef6\u4e2d\u7684\u5bc6\u94a5\u662f\u5426\u6b63\u786e\u3002\u786e\u4fdd\u5728 Tavily\u3001Brave \u6216 Volcengine \u5e73\u53f0\u6ce8\u518c\u5e76\u83b7\u53d6\u6709\u6548\u5bc6\u94a5\u3002<\/li>\n<li><strong>\u662f\u5426\u9700\u8981\u7f16\u7a0b\u7ecf\u9a8c\uff1f<\/strong><br \/>\n\u57fa\u672c\u4f7f\u7528\u65e0\u9700\u7f16\u7a0b\u7ecf\u9a8c\uff0c\u4f46\u914d\u7f6e\u73af\u5883\u548c\u81ea\u5b9a\u4e49\u5de5\u4f5c\u6d41\u9700\u8981\u57fa\u7840 Python \u77e5\u8bc6\u3002<\/li>\n<li><strong>\u5982\u4f55\u4f18\u5316\u641c\u7d22\u7ed3\u679c\uff1f<\/strong><br \/>\n\u5728\u00a0<code>conf.yaml<\/code>\u00a0\u4e2d\u8c03\u6574\u00a0<code>max_results<\/code>\u00a0\u548c\u00a0<code>search_engine<\/code>\u00a0\u53c2\u6570\uff0c\u9009\u62e9\u66f4\u9002\u5408\u7684\u641c\u7d22\u5f15\u64ce\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>DeerFlow \u662f\u7531\u5b57\u8282\u8df3\u52a8\u5f00\u6e90\u7684\u4e00\u4e2a\u6df1\u5ea6\u7814\u7a76\u6846\u67b6\uff0c\u65e8\u5728\u901a\u8fc7\u591a\u667a\u80fd\u4f53\u534f\u4f5c\u5b9e\u73b0\u7814\u7a76\u4efb\u52a1\u7684\u81ea\u52a8\u5316\u3002\u5b83\u7ed3\u5408\u4e86\u8bed\u8a00\u6a21\u578b\u548c\u4e13\u4e1a\u5de5\u5177\uff0c\u5982\u7f51\u9875\u641c\u7d22\u3001\u7f51\u9875\u722c\u866b\u548c Python \u4ee3\u7801\u6267\u884c\uff0c\u5e2e\u52a9\u7528\u6237\u9ad8\u6548\u5b8c\u6210\u590d\u6742\u7684\u7814\u7a76\u4efb\u52a1\u3002DeerFlow \u57fa\u4e8e LangCh&#8230;<\/p>\n","protected":false},"author":1,"featured_media":62352,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20,419,427],"tags":[230,389],"class_list":["post-31963","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","category-ai-learning","category-research-assistant","tag-aikaiyuanxiangmu","tag-shengchengshenduyanjiuao"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/31963","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/comments?post=31963"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/31963\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media\/62352"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media?parent=31963"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/categories?post=31963"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/tags?post=31963"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}