Scaling

You had an idea of how many people would use your search app, but suddenly, it became so popular that the number of requests you're making is three times bigger than you thought. That's not a problem. You don't have to do anything about it - we take care of it for you. deepset Cloud uses autoscaling, which automatically adjusts the infrastructure to your needs. You don't have to worry you'll hit a request limit or that the speed of your search will drop.

Speed

Autoscaling ensures that your pipeline performs at a certain speed. The average query latency in deepset Cloud is less than 500 ms. If you have special requirements for latency, just reach out to our Solution Engineers.

Pipeline Statistics

The deepset Cloud dashboard gives you basic information about your pipeline, such as the average response time or the number of searches ran. If you want to check what queries were asked, the top answers, and how long it took to find them, click the name of the pipeline on the Pipelines page. This brings you to Pipeline Details, where you can view all the information about your pipeline.

Monitoring Pipelines

📘

Changes on their way

We're still actively working on this feature to make it better. This page describes its current, first implementation. We'll be updating it soon to make it smoother.

Check pipeline logs to see what happened since it was deployed. You can view the logs on the Pipeline Details page (just click the pipeline name to get there). Expand messages for more details and possible actions.