Today for AI
HOT RADAR
toolsHEAT 10.9°

AI CURATED HOT STORY · 10/21/2026

Tencent Cloud Opens Yuanbao Search API with Billion-Scale Indexing

1 reports archived1 independent sourcesupdated 10/21/2026, 11:00:53
Synthesis & Latest Updates
1 Sources Cross-Validated

Tencent Cloud has officially opened its Yuanbao Search API to external developers. Built on LLM technology with a billion-scale index and integration of 157 vertical industry sources, the service features a novel hybrid indexing architecture that reduces average retrieval latency to 8ms and ranking inference time to 30ms, aiming to provide high-recall, low-latency structured search for Agent and LLM applications.

LATEST/Tencent Cloud has officially opened its Yuanbao Search API to external developers. Built on LLM technology with a billion-scale index and integration of 157 vertical industry sources, the service features a novel hybrid indexing architecture that reduces average retrieval latency to 8ms and ranking inference time to 30ms, aiming to provide high-recall, low-latency structured search for Agent and LLM applications.

HEAT TRENDHourly heat curve

4 fully observed hours
Now
10.9
Peak
11.712:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·68 pts
    • Yuanbao Search has built a billion-scale index serving hundreds of millions of daily calls, covering 157 sources across 13 vertical industries like finance and healthcare.
    • It employs a hybrid architecture combining inverted, vector, and fusion-optimized indices, achieving an average retrieval latency of 8ms while maintaining a 94% recall rate.
    • By pre-compressing document tokens into cache, core ranking model inference time was reduced from 149ms to 30ms, significantly optimizing end-to-end response speed.
Tencent Cloud Opens Yuanbao Search API with Billion-Scale Indexing | Today for AI