{"id":297,"date":"2023-10-08T09:44:08","date_gmt":"2023-10-08T01:44:08","guid":{"rendered":"https:\/\/myhelpfulai.com\/?p=297"},"modified":"2023-10-08T09:44:08","modified_gmt":"2023-10-08T01:44:08","slug":"lai-zi-wei-ruan-de-autogen","status":"publish","type":"post","link":"https:\/\/aitimes.link\/index.php\/2023\/10\/08\/lai-zi-wei-ruan-de-autogen\/","title":{"rendered":"\u6765\u81ea\u5fae\u8f6f\u7684AutoGen"},"content":{"rendered":"\n

https:\/\/microsoft.github.io\/autogen\/<\/a><\/p>\n\n\n\n

AutoGen is a framework that enables development of LLM applications using multiple agents that can converse with each other to solve task. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.
\u6765\u81ea\u5b98\u65b9\u7684\u7b80\u4ecb\uff1a\u5927\u6982\u63cf\u8ff0\u8d77\u6765\u5c31\u662f\u57fa\u4e8eLLM\u6a21\u578b\uff0c\u4f7f\u7528\u591a\u89d2\u8272\u4e92\u52a8\u6765\u5206\u89e3\u3001\u89e3\u51b3\u95ee\u9898\u7684\u6846\u67b6\u3002\u76ee\u524d\u5df2\u7ecf\u51fa\u73b0\u4e86\u591a\u4e2a\u7c7b\u4f3c\u7684\uff0c\u6bd4\u5982\u4e4b\u524d\u6587\u7ae0<\/a>\u91cc\u9762\u5199\u8fc7\u7684MetaGPT<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n

Main Features\u200b<\/a><\/h3>\n\n\n\n
    \n
  • AutoGen enables building next-gen LLM applications based on multi-agent conversations<\/strong> with minimal effort. It simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcome their weaknesses.<\/li>\n\n\n\n
  • It supports diverse conversation patterns<\/strong> for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy, the number of agents, and agent conversation topology.<\/li>\n\n\n\n
  • It provides a collection of working systems with different complexities. These systems span a wide range of applications<\/strong> from various domains and complexities. They demonstrate how AutoGen can easily support different conversation patterns.<\/li>\n\n\n\n
  • AutoGen provides a drop-in replacement of openai.Completion<\/code> or openai.ChatCompletion<\/code> as an enhanced inference API<\/strong>. It allows easy performance tuning, utilities like API unification & caching, and advanced usage patterns, such as error handling, multi-config inference, context programming etc.<\/li>\n<\/ul>\n\n\n\n

    The figure below shows the built-in agents in AutoGen.\u00a0
    <\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n

    <\/p>\n","protected":false},"excerpt":{"rendered":"

    https:\/\/microsoft.github.io\/autogen\/ AutoGen is a frame […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-297","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/297","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/comments?post=297"}],"version-history":[{"count":1,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/297\/revisions"}],"predecessor-version":[{"id":301,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/297\/revisions\/301"}],"wp:attachment":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/media?parent=297"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/categories?post=297"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/tags?post=297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}