// AI news · 2026-11-06 · Google Cloud
Google Launches AI.AGG Semantic Aggregation in BigQuery
Google introduces AI.AGG, a native semantic aggregation function in BigQuery that enables natural-language queries over millions of rows of text and multimodal data.
Published 2026-11-06 01:00 (Beijing time)Source Google CloudAuto-summarised, fact-checked against source
01Summary
It uses distributed map-reduce with Gemini LLMs for safe batching, parallel inference, and recursive synthesis. The solution eliminates external pipelines, supports direct image input via Object Tables, and relies on full-weight LLMs throughout the pipeline.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- AI.AGG enables semantic aggregation over millions of rows in BigQuery using natural language queries.
- It uses distributed map-reduce with Gemini LLMs for safe batching, parallel processing, and recursive synthesis.
- Supports both text and multimodal inputs via BigQuery Object Tables without data movement or transcoding.
- Relies on full-weight LLMs at every stage, unlike row-level functions that use distilled models.
03Source
Semantic aggregation over millions of rows in BigQuery with AI.AGG
Google Cloud · published 2026-11-06 01:00 Beijing time
05Related news
- Same source · Google uses AlphaEvolve and Harbor to optimize agent skills2026-11-06 · Google Cloud
- Same source · Google Public Sector Summit: Mission Meets Moonshot2026-11-05 · Google Cloud
- Same topic · Ryzova Launches Alphi v1 Multimodal AI Model2026-11-06 · Hugging Face Forum
- Same topic · Google refuses school opt-out of AI overviews2026-11-05 · WIRED
- Same day · NVIDIA DSX OS Enables GPU Kubernetes Configuration and Operation2026-11-06 · NVIDIA
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-06 · Archive by date · All AI news · Today