Diogo Almeida 用 Jev 并行做可视化解释
playing around with visual explainers of novel patterns leveraging jev's parallelism
Diogo Almeida 表示正在尝试用 Jev 的并行能力,为新颖模式制作可视化解释。他引用了 Allie the Icon 介绍的 Jev "逐行搜索"模式:把整份文档放进 state,再对每一行或每一段提问,适合找出与查询最相关的那一行;预期只有一个主导答案时用 nouls,想按整体相关性高亮各行时用 scores。
查看原帖我最喜欢的 Jev 模式之一是“逐行搜索”,即把整份文档放进 state,然后对每一行(或每一段)提问。当你想为某个查询找出最相关的那一行时,这非常有用。 当你预期只有一个主导答案时用 nouls,当你想按整体相关性高亮各行时用 scores。前者适合回答某个具体问题,后者适合找出所有相关段落。
查看原文
One of my favorite Jev patterns is "line-by-line search", where you put an entire document in state, and ask a question for each line (or paragraph). This is super useful when you want to find the most relevant line for a query. Use nouls when you expect one dominate answer, use scores when you want to highlight lines by overall relevance. The former is good for answering a specific question while the latter is good for finding all relevant passages.
正文 · AI 翻译
尝试利用 Jev 的并行能力,为新颖模式制作可视化解释