<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Openai on RekCore</title><link>https://rekcore.com/tags/openai/</link><description>Recent content in Openai on RekCore</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><copyright>© 2026 RekCore</copyright><lastBuildDate>Wed, 06 May 2026 10:00:00 -0500</lastBuildDate><atom:link href="https://rekcore.com/tags/openai/index.xml" rel="self" type="application/rss+xml"/><item><title>Build a RAG Application with LangChain</title><link>https://rekcore.com/tutorials/2026-05-06-build-rag-with-langchain/</link><pubDate>Wed, 06 May 2026 10:00:00 -0500</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-build-rag-with-langchain/</guid><description/></item><item><title>GPT-5 Officially Launches with Advanced Multimodal Reasoning</title><link>https://rekcore.com/news/2026-05-06-gpt5-launch/</link><pubDate>Wed, 06 May 2026 09:00:00 +0000</pubDate><guid>https://rekcore.com/news/2026-05-06-gpt5-launch/</guid><description/></item><item><title>AI Agent 动不动就翻车？六层 Harness 架构让你告别玄学调参</title><link>https://rekcore.com/tutorials/2026-05-06-harness-engineering-six-layers/</link><pubDate>Wed, 06 May 2026 12:00:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-harness-engineering-six-layers/</guid><description>AI Agent 频繁跑偏、死循环、成功率卡在 70%？北大博士后卢菁和一线团队的经验表明，真正的瓶颈是 Harness——模型外面的运行系统。本文详解六层架构设计。</description></item><item><title>Building Agentic Workflows with Function Calling</title><link>https://rekcore.com/tutorials/2026-05-03-agentic-workflows/</link><pubDate>Sun, 03 May 2026 11:00:00 -0500</pubDate><guid>https://rekcore.com/tutorials/2026-05-03-agentic-workflows/</guid><description/></item></channel></rss>