BriefsNewsAvailable now1 min read

OpenAI shares how it scales AI storage on Azure Cosmos DB

OpenAI details the engineering behind Habitat, its multi-tenant storage platform built on Azure Cosmos DB for ChatGPT users.

OpenAI shares how it scales AI storage on Azure Cosmos DB — image from OpenAI
Image: OpenAI

Summary

OpenAI published a technical review of Habitat, the online storage platform that supports its AI products. The post details how the team moved back to a multi-tenant design using Azure Cosmos DB and a custom serverless mode to handle massive traffic. These updates reduced global read p50 latency from 120 ms to 10 ms.

What changed

  • Reverted from single-tenant backing containers back to a default multi-tenant Azure Cosmos DB container design.
  • Adopted a custom serverless mode where physical partitions scale up to 10K RU/s with RU-usage-based splits.
  • Reduced global read p50 latency from 120 ms to 10 ms.

Availability

Available now

“Today, Habitat is a multi-tenant database layer for many OpenAI products, but we went through a circular journey from using one multi-tenant Azure Cosmos DB container to provisioning single-tenant backing containers to reverting to a multi-tenant container by default.”

Founder takeaway

Engineering teams managing large databases can review these architecture changes to handle high-throughput multi-tenant loads.

Source

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS logo on a FounderHeist card

    NewsAvailable now

    Amazon Quick adds smart approvals for agentic AI actions

    Amazon Quick introduces smart approvals to automate routine agentic tasks while keeping human oversight for high-impact actions.

    AWS1 min read

  2. ElevenLabs introduces Cue forced alignment AI model — image from ElevenLabs

    NewsAvailable now

    ElevenLabs introduces Cue forced alignment AI model

    ElevenLabs releases Cue, an AI forced alignment model that places every character in an audio file on a precise timeline and powers its Scribe model family.

    ElevenLabs1 min read

  3. GitHub makes Copilot Memory generally available on paid Copilot plans — image from GitHub

    NewsAvailable now

    GitHub makes Copilot Memory generally available on paid Copilot plans

    GitHub introduces new AI intelligence capabilities including Copilot Memory, dreaming, and multi-repository code search.

    GitHub1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.