检索

检索 (retrieval)

概念
本站收录 4 集 · 11 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

11 条

检索是容易的。值得检索才是产品。
Retrieval is easy. Being worth retrieving from is the product.
—— Garry Tan · [13:21]

指向原始笔记的链接

一个没有人策划的大脑会变成垃圾场,优秀的搜索检索会以绝对的信心检索出一个陈旧的事实。
A brain nobody curates becomes a garbage dump with great search retrieval will surface a stale fact with total confidence.
—— Garry Tan · [14:30]

指向原始笔记的链接

结果证明总结实际上损害了检索。
And it turns out that summarization actually hurts a retrieval.
—— Mikael · [26:03]

指向原始笔记的链接

当你翻转这个剧本时,结果是你可以用更小的分块大小获得更好的检索质量,否则这是不可能的。
When you flip that script, it turns out you can get better retrieval quality with a smaller chunk size, which otherwise is not possible.
—— 嘉宾 · [41:34]

指向原始笔记的链接

大多数人认为嵌入模型已经商品化了,但这不是事实。根据你选择什么样的嵌入模型,你在检索质量上可能会有非常巨大的差别。
Most people think embedding models are commoditized, and that is not true. There is a very big difference that you can get in retrieval quality based on what embedding model you choose.
—— 嘉宾 · [50:00]

指向原始笔记的链接

所以我要主张,如果我们必须干掉某个东西,如果有什么必须死,那很可能是检索调优。
So I will claim that if we have to kill something, if something has to be dead, then it’s probably retrieval tuning.
—— Yuval Belfer · [02:40]

指向原始笔记的链接

在这种情况下,你可以把检索本质上就理解为投票。
In this case, you can think of retrieval as essentially just voting.
—— Yuval Belfer · [12:48]

指向原始笔记的链接

如果我需要给你们留下一句话,我会说智能体并没有杀死检索。
And if I need to leave you with something, I would say that agents didn’t kill retrieval.
—— Yuval Belfer · [16:54]

指向原始笔记的链接

在合适的地方,我们不是用 LLM 替换检索和排序系统,而是把推理和理解蒸馏进某种生产级排序架构。
Where it seems right, we’re not replacing the retrieval and ranking system with an LLM, but rather distilling the reasoning and understanding into some production ranking architecture.
—— Raghav Saboo · [09:06]

指向原始笔记的链接

其中最重要的一点是,代码已经在磁盘上、在本地了,尤其是如果你的智能体有上下文的话,那为什么要用一个预检索系统把它复杂化呢?
And the largest part there is code is already on disk and local, especially if your agent has context, so why complicate it with a pre-retrieval system?
—— George He · [03:49]

指向原始笔记的链接

但这里的主要结论其实是,它最终归结为你所拥有的数据的规模,以及你愿意投入多少整理成本来维护那套合理的检索系统或数据管理系统。
But the major takeaway here is actually it really comes down to the scale of the data that you have and how much curation effort you’re going to put in in order to maintain that retrieval system or that data management system that makes sense, right?
—— George He · [05:18]

指向原始笔记的链接

② 出现在这些集

4 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · LLM · 记忆 · OpenAI · Claude · Kay Malcolm · Paula Dozsa · Daniel Whitenack · Raghav Saboo · Oracle