<?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>选型 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E9%80%89%E5%9E%8B/</link><description>Recent content in 选型 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>Thu, 16 Jul 2026 10:34:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%80%89%E5%9E%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>向量数据库选型指南：从原理对比到生产实践</title><link>https://guijiagi.com/posts/b2-eff997cf/</link><pubDate>Thu, 16 Jul 2026 10:34:00 +0800</pubDate><guid>https://guijiagi.com/posts/b2-eff997cf/</guid><description>深度对比主流向量数据库的架构设计与性能特征，提供不同应用场景下的选型决策框架</description></item><item><title>视觉模型选型2026：从图像理解到多模态推理</title><link>https://guijiagi.com/posts/vision-model-2026-selection/</link><pubDate>Thu, 02 Jul 2026 10:54:00 +0800</pubDate><guid>https://guijiagi.com/posts/vision-model-2026-selection/</guid><description>2026年视觉语言模型全面选型指南，覆盖OCR、图表理解、视频分析等场景</description></item><item><title>向量数据库2026选型：Milvus vs Pinecone vs Weaviate vs Qdrant</title><link>https://guijiagi.com/posts/vector-database-2026-comparison/</link><pubDate>Tue, 30 Jun 2026 09:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/vector-database-2026-comparison/</guid><description>从性能、功能、成本、生态四个维度深度对比四大向量数据库，附2026年最新基准测试数据</description></item><item><title>2026开源大模型选型指南</title><link>https://guijiagi.com/posts/opensource-llm-selection-2026/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/opensource-llm-selection-2026/</guid><description>2026开源大模型选型指南</description></item><item><title>Agent后端模型选型建议</title><link>https://guijiagi.com/posts/agent-backend-model-selection/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-backend-model-selection/</guid><description>Agent后端模型选型建议</description></item><item><title>多模态模型选型指南</title><link>https://guijiagi.com/posts/multimodal-model-selection-guide/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/multimodal-model-selection-guide/</guid><description>多模态模型选型指南</description></item><item><title>函数调用模型选型</title><link>https://guijiagi.com/posts/function-calling-model-selection/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/function-calling-model-selection/</guid><description>函数调用模型选型</description></item><item><title>嵌入模型选型指南</title><link>https://guijiagi.com/posts/embedding-model-selection-guide/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/embedding-model-selection-guide/</guid><description>嵌入模型选型指南</description></item><item><title>向量数据库选型：智能体记忆系统实践</title><link>https://guijiagi.com/posts/agent-memory-vector-db/</link><pubDate>Fri, 26 Jun 2026 14:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-memory-vector-db/</guid><description>从实际 Agent 记忆系统需求出发，深入对比 Pinecone、Milvus、Qdrant 等主流向量数据库的架构、性能与适用场景。</description></item><item><title>多模态大模型选型：GPT-5V vs Gemini vs Qwen-VL vs LLaVA</title><link>https://guijiagi.com/posts/multimodal-model-selection/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/multimodal-model-selection/</guid><description>全面对比 2026 年主流多模态大模型：GPT-5o、Gemini 2.0 Pro、LLaVA-1.6、Qwen-VL2、InternVL3 在图像、视频、文档理解上的表现与选型建议。</description></item><item><title>微调 vs RAG：什么场景该选什么方案</title><link>https://guijiagi.com/posts/fine-tuning-vs-rag-decision/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/fine-tuning-vs-rag-decision/</guid><description>从知识更新频率、推理深度、成本预算、数据隐私等维度，系统对比微调与 RAG 的适用场景，给出决策框架和混合方案。</description></item><item><title>2026 AI 视频工具对比：10 款主流工具深度横评</title><link>https://guijiagi.com/posts/ai-video-comparison-2026/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-video-comparison-2026/</guid><description>10款主流AI视频工具深度横评，涵盖画质、时长、价格、适用场景对比及选型决策树</description></item><item><title>2026 LLM 选型指南：GPT/Claude/Gemini/DeepSeek/Qwen 怎么选</title><link>https://guijiagi.com/posts/llm-model-selection-2026/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-model-selection-2026/</guid><description>2026 年主流大语言模型全面选型指南，涵盖能力对比、API 价格、场景推荐与决策框架</description></item><item><title>Embedding 模型选型：OpenAI/BGE/E5/Novus 对比</title><link>https://guijiagi.com/posts/embedding-model-selection/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/embedding-model-selection/</guid><description>Embedding 模型深度选型指南，涵盖 MTEB 排行、维度存储、多语言支持与领域微调</description></item><item><title>Reranker 模型选型：Cohere/BGE/Cross-Encoder 对比</title><link>https://guijiagi.com/posts/reranker-model-selection/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/reranker-model-selection/</guid><description>Reranker 模型在 RAG 中的关键角色，Bi-Encoder vs Cross-Encoder 原理与选型策略</description></item><item><title>主流智能体平台终极对比：2026 选型全景图</title><link>https://guijiagi.com/posts/mainstream-agent-recap/</link><pubDate>Wed, 24 Jun 2026 16:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/mainstream-agent-recap/</guid><description>OpenAI/Anthropic/Dify/Coze/LangChain/CrewAI/AutoGen/OpenClaw 终极对比，附选型决策树与成本分析</description></item></channel></rss>