Skip to content

agentic ai collections

学习AI应用的资料汇总

· 2 min ·

Beginning#

Recently I’ve been in a “World Top 500” company for internship, and my JD is Data/AI intern.

Yeah, you may guess it right, I’ve been in Bosch for 3 days when I write this short.

So I would like to share some documents, to record the path to mastering agentic AI.

需要思考复习几个点:

  • RAG的流程
  • Embedding的BM25和Sparse方案有什么区别
  • Rerank的原理是什么,为什么RFF融合重排后还要Rerank。
  • 评估RAG性能的常用指标有哪些(Precision, Recall, MRR, Hit Rate)

Resources#

Learning Points#

检索+生成 2阶段评估指标#

阶段评估对象常用指标
Retrieval(召回)Top-K 文档的相关性Recall@K, MRR, Precision@K, nDCG
Generation(生成 / Rerank + LM)最终生成答案质量Exact Match (EM), F1-score, BLEU, ROUGE, METEOR, QA-specific metrics

在检索阶段的指标:创建真实情况(知道哪些文档与给定查询相关)可能耗时耗力,通常需要人工标注(Ground Truth)。

Browser Use#

最近在实习探索浏览器自动化的agent,发现browser-use的sdk开源了,基于playwright改造的新增agentic AI的运行框架,还有官方的cloud平台支持云端托管。