Legora 搜索延迟问题因数据库分区解决，AI21 多尺寸索引提升召回率，SID.ai 搜索模型效率提升

Notes from classroom: - Legora's search latency went from 100 milliseconds to twenty seconds at the...

Notes from classroom: - Legora's search latency went from 100 milliseconds to twenty seconds at the 99th percentile once finished legal projects and live ones shared database partitions. One namespace per project fixed it. - About half the sites Liad Yosef's team tested publish an llms.txt file for agents. Almost none of the agents they ran read it. They went to the docs page, then the homepage. - AI21 indexed the same data at six chunk sizes and let hindsight pick the best size per query. Recall improved something like 20 to 40 percent over any single fixed size, so now they index at several sizes at once and merge the rankings. - Agents spend 30 to 50 percent of their tokens on search. SID.ai 's RL trained search model does the task about twenty times faster than a frontier model at roughly a hundredth of the cost. - An agent searching a contract for "30 days" cannot tell a deadline from a grace period from a retention rule. Code, full of exact names to grep for, was the easy case. Search & Retrieval playlist: youtube.com/watch?v=IN-rb-… 💬 1 🔄 2 ❤️ 1 👀 306 📊 2 ⚡