Latest update on enabling real-time AI with Streaming Ingestion in Vertex AI | C2C Community

Latest update on enabling real-time AI with Streaming Ingestion in Vertex AI

  • 21 September 2022
  • 3 replies
  • 21 views

Userlevel 7
Badge +13

We know how difficult it is to solve problems like fraud detection, ad targeting, and recommendation engines, which require near real-time predictions. The accuracy of these predictions is heavily reliant on access to the most recent data, with delays of just a few seconds making all the difference.
However, it is difficult to set up the infrastructure required to support high-throughput updates and low-latency data retrieval.


3 replies

Userlevel 7
Badge +56

I read their post the day it was uploaded. And I find it amazing. Still there is the issue of the few seconds latency. But still it is amazing.

What do you think @malamin?

Userlevel 7
Badge +13

This is the next hope @ilias ,

Still there is the issue of the few seconds latency

The latency issue, not only relies on the server but also on the client side at times. In addition to internet speed and bandwidth, CDN, routing, and background running applications, irresponsible browser activity can lead to latency issues. Yes, it is still good, and it will get better in the future.

Thank you for bringing up a good point for discussion.

Userlevel 7
Badge +56

LOL

But the client is never wrong. Everything works fine on their machine, right? 😂

I’m glad that we agree on that @malamin 

Reply