AI 导读
Perplexity 发布搜索基础设施 Photon，p99 响应时间从约 800 ms 降至约 65 ms，服务器用量减少约 20%，单文档可存储的数据量提升至 2.5 倍。官方同时给出 Photon 的构建说明，并开放 Fast Search 的使用入口。
正文
Inside Photon, p99 response time dropped from about 800 ms to about 65 ms. It uses about 20% fewer serving machines and stores 2.5x as much data per document.
How we built Photon: https://t.co/7c64kR5OB5
Get started with Fast Search: https://t.co/Qn4OPZfqnx
来源：@perplexity_ai · x.com