{"version":1,"type":"story","url":"https://digestai.news/story/perplexity-introduces-photon-a-rust-based-retrieval-engine","json":"https://digestai.news/story/perplexity-introduces-photon-a-rust-based-retrieval-engine.json","markdown":"https://digestai.news/story/perplexity-introduces-photon-a-rust-based-retrieval-engine.md","slug":"perplexity-introduces-photon-a-rust-based-retrieval-engine","headline":"Perplexity introduces Photon, a Rust-based retrieval engine","summary":"Perplexity has launched Photon, a new in‑house retrieval and ranking engine written in Rust that now handles all production traffic and powers a Fast Search mode in its API. Photon reports single‑call latency of 160 ms at p50 and 230 ms at p95, and the engine can be accessed as a hosted API for $1 per 1,000 requests.\n\nThe new engine replaces an older forked open‑source engine that suffered from high tail latency (p99 near 800 ms), merge spikes, and slow recovery. Fast Search, tuned for agentic workflows, achieved 64.3 % on 3,554 benchmark tasks at an estimated cost of $59.73, about 68 % cheaper than the default preset.\n\nPerplexity notes that Fast Search trades a small drop in relevance (DCG from 2.45 to 2.21) and answer availability (0.596 to 0.567) for lower cost and faster performance, recommending it for day‑to‑day agent loops while keeping the default preset for hard queries.","keyPoints":["Photon reduces p99 latency from ~800 ms to ~65 ms and runs on 20 % fewer machines","Fast Search costs $59.73 for 3,554 tasks, 68 % cheaper than the default preset","Photon is a hosted API; pay $1 per 1,000 requests and it is not open source"],"whyItMatters":"The upgrade shows how Rust‑based infrastructure can dramatically lower search latency and cost for AI‑powered agents, benefiting companies that rely on fast, scalable retrieval.","category":{"slug":"enterprise","name":"Enterprise & Industry","url":"https://digestai.news/category/enterprise"},"entities":{"companies":["Perplexity"],"models":[],"people":[]},"firstPublishedAt":"2026-09-30T08:26:52Z","updatedAt":"2026-09-30T08:26:52Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Perplexity Introduces Photon: A Rust-Based Retrieval Engine That Cuts p99 Latency From 800 ms to 65 ms","url":"https://marktechpost.com/2026/09/30/perplexity-introduces-photon-a-rust-based-retrieval-engine-that-cuts-p99-latency-from-800-ms-to-65-ms","publishedAt":"2026-09-30T08:26:52Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Perplexity introduces Photon, a Rust-based retrieval engine\", 30 September 2026, https://digestai.news/story/perplexity-introduces-photon-a-rust-based-retrieval-engine","publisher":"Digest AI","title":"Perplexity introduces Photon, a Rust-based retrieval engine","datePublished":"2026-09-30T08:26:52Z","url":"https://digestai.news/story/perplexity-introduces-photon-a-rust-based-retrieval-engine"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}