<?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>Vertex AI on 梦兽编程</title><link>https://rexai.top/tags/vertex-ai/</link><description>Recent content in Vertex AI on 梦兽编程</description><generator>Hugo -- 0.163.3</generator><language>zh-cn</language><copyright>梦兽编程</copyright><lastBuildDate>Tue, 21 Jul 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://rexai.top/tags/vertex-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>BigQuery AI.AGG 深度解析：当 GROUP BY 开始调用 Gemini</title><link>https://rexai.top/ai/llm/bigquery-ai-agg/</link><pubDate>Tue, 21 Jul 2026 10:00:00 +0800</pubDate><guid>https://rexai.top/ai/llm/bigquery-ai-agg/</guid><description>Google 把 Gemini 接进 BigQuery 聚合函数：AI.AGG 能对文本和图片执行多级批处理，每组返回一个自然语言结论。本文从 SQL 语义、执行机制、成本边界和工程治理四个角度，分析它何时有用、何时危险。</description></item></channel></rss>