From the source
Lead story
Top stories
Models & availability
Latest
Lead story
Top stories
Models & availability
Latest
From the source
In-house retrieval and ranking engine for AI search
Perplexity built Photon, an in-house retrieval and ranking engine designed to replace an open-source platform that faced scaling costs, tail latency, and recovery time constraints.
Photon powers Perplexity's search pipeline and a new fast preset for its Search API, achieving single-search-call latency of 160 ms at p50 and 230 ms at p95, and reducing estimated model-plus-search cost per task by 68% across six public benchmarks while maintaining comparable task quality.
From the source
Photon now powers our search pipeline and is also the foundation of a new fast preset for our Search API, with single-search-call latency of 160 ms at p50 and 230 ms at p95. Across six public benchmarks, the fast preset reduced estimated model-plus-search cost per task by 68% while maintaining aggregate task quality comparable to the default preset.
perplexity.ai