{"id":26252,"date":"2025-01-04T17:26:42","date_gmt":"2025-01-04T09:26:42","guid":{"rendered":"https:\/\/www.1ai.net\/?p=26252"},"modified":"2025-01-04T17:26:42","modified_gmt":"2025-01-04T09:26:42","slug":"%e9%98%bf%e9%87%8c%e5%8f%91%e5%b8%83-qwen-agent-%e6%a1%86%e6%9e%b6%ef%bc%8c%e8%b5%8b%e8%83%bd%e5%bc%80%e5%8f%91%e8%80%85%e6%9e%84%e5%bb%ba%e5%a4%8d%e6%9d%82-ai-%e6%99%ba%e8%83%bd%e4%bd%93","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/26252.html","title":{"rendered":"Ali Releases Qwen-Agent Framework to Empower Developers to Build Complex AI Intelligence Bodies"},"content":{"rendered":"<p>January 4 news.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%98%bf%e9%87%8c\" title=\"[View articles tagged with [Ali]]\" target=\"_blank\" >Ali<\/a>Tongyi Qianqian Qwen introduces Qwen-Agent, a new AI framework.<strong>Based on the existing Qwen language model, supports<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%99%ba%e8%83%bd%e4%bd%93\" title=\"[View articles tagged with [intelligent body]]\" target=\"_blank\" >Agent<\/a>Performs complex tasks and provides a variety of advanced features to empower developers to build more powerful AI intelligences.<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-26253\" title=\"1f3f2125j00spk4vr00t5d000v900hip\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/01\/1f3f2125j00spk4vr00t5d000v900hip.jpg\" alt=\"1f3f2125j00spk4vr00t5d000v900hip\" width=\"1125\" height=\"630\" \/><\/p>\n<p>The official introduction is attached as follows:<\/p>\n<blockquote>\n<ul>\n<li>Qwen-Agent is a development framework. Developers can build Agent applications based on this framework to take full advantage of the command following, tool usage, planning, and memorization capabilities based on the generalized Qwen model. This project also provides sample applications such as browser assistants, code interpreters, and custom assistants.<\/li>\n<\/ul>\n<\/blockquote>\n<p>The framework builds on Qwen's existing language model, empowering intelligences with core capabilities such as executing detailed instructions, using tools, planning tasks, and maintaining dialog context, as well as integrating advanced functionality such as RAG (Retrieval Augmented Generation), a code interpreter, and specialized mathematical reasoning based on Qwen2.5-Math.<\/p>\n<p>In terms of architecture, Qwen-Agent utilizes a two-tier architecture. The bottom layer provides the language model and basic tools, while the top layer provides off-the-shelf intelligence components. Developers have the flexibility to combine these components to build intelligences that can perform complex tasks such as reading PDFs, manipulating existing tools, and performing custom functions.<\/p>\n<p>Developers can deploy Qwen models through Alibaba's DashScope cloud service or on their own, and Alibaba recently lowered the price of its API AI service to further lower the threshold for use. In addition, the framework also provides a GUI interface, making it easy for developers to create interactive web presentations using the Gradio framework.<\/p>","protected":false},"excerpt":{"rendered":"<p>January 4 news, Ali Tongyi Qwen launched a new AI framework Qwen-Agent, based on the existing Qwen language model, support for intelligent bodies to perform complex tasks, and provide a variety of advanced features to empower developers to build a more powerful AI intelligent body. The official introduction is attached as follows: Qwen-Agent is a development framework. Developers can develop Agent applications based on this framework to fully utilize the command following, tool usage, planning, and memory capabilities based on the Qwen model. The project also provides sample applications such as browser assistants, code interpreters, and custom assistants. The framework builds on Qwen's existing language model and empowers intelligences to execute detailed instructions, use tools, plan tasks, and maintain their memory.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1355,1759],"collection":[],"class_list":["post-26252","post","type-post","status-publish","format-standard","hentry","category-news","tag-1355","tag-1759"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/26252","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=26252"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/26252\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=26252"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=26252"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=26252"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=26252"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}