<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>工程实践 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%B7%A5%E7%A8%8B%E5%AE%9E%E8%B7%B5/</link><description>Recent content in 工程实践 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 30 Jun 2026 10:50:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%B7%A5%E7%A8%8B%E5%AE%9E%E8%B7%B5/index.xml" rel="self" type="application/rss+xml"/><item><title>结构化输出技术：从JSON Mode到Function Calling</title><link>https://guijiagi.com/posts/structured-output-json-mode-to-function-calling/</link><pubDate>Tue, 30 Jun 2026 10:50:00 +0800</pubDate><guid>https://guijiagi.com/posts/structured-output-json-mode-to-function-calling/</guid><description>全面介绍2026年LLM结构化输出技术，包括JSON Mode、Function Calling、Constrained Decoding等方案及其实际应用</description></item><item><title>RAG 常见故障排查：幻觉、漏检、延迟的根因分析</title><link>https://guijiagi.com/posts/rag-troubleshooting-hallucination-miss-retrieval-latency/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-troubleshooting-hallucination-miss-retrieval-latency/</guid><description>系统梳理 RAG 系统中的高频故障模式，提供从症状到根因的诊断框架和修复方案</description></item><item><title>RAG 分块策略深度对比：语义分块 vs 文档感知 vs 层级分块</title><link>https://guijiagi.com/posts/rag-chunking-strategies-semantic-vs-document-aware-vs-hierarchical/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-chunking-strategies-semantic-vs-document-aware-vs-hierarchical/</guid><description>深入对比 2026 年主流 RAG 分块策略，包含实验数据、代码实现和选型建议</description></item><item><title>RAG 数据管道设计：从 PDF/HTML/数据库到高质量知识库</title><link>https://guijiagi.com/posts/rag-data-pipeline-pdf-html-database-to-knowledge-base/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-data-pipeline-pdf-html-database-to-knowledge-base/</guid><description>系统讲解 RAG 数据管道的工程设计，涵盖文档解析、清洗、增强、质量控制和自动化运维</description></item><item><title>多模态 RAG 实战：图文混合检索的工程实现</title><link>https://guijiagi.com/posts/multimodal-rag-image-text-hybrid-retrieval/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/multimodal-rag-image-text-hybrid-retrieval/</guid><description>深入多模态 RAG 的工程实现，涵盖图文统一编码、混合检索策略、跨模态重排序等核心技术</description></item><item><title>大模型增量训练实践</title><link>https://guijiagi.com/posts/llm-incremental-training/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-incremental-training/</guid><description>大模型增量训练的工程实践，从数据准备到训练优化的全链路指南</description></item></channel></rss>