<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Json-Schema on Chen Kai Blog</title><link>https://www.chenk.top/zh/tags/json-schema/</link><description>Recent content in Json-Schema on Chen Kai Blog</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Thu, 02 Apr 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/zh/tags/json-schema/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型工程（七）：Function Calling 实战</title><link>https://www.chenk.top/zh/llm-engineering/07-function-calling/</link><pubDate>Thu, 02 Apr 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/zh/llm-engineering/07-function-calling/</guid><description>&lt;p>函数调用是大语言模型（LLM）连接外部世界的关键接口，也是 chat template、结构化输出内核与提示工程的交汇点。本章将深入剖析底层机制，探讨哪些行为具备可依赖的确定性保证，以及哪些 agent-loop 模式能在真实生产负载下稳定运行。&lt;/p></description></item></channel></rss>