Performance and Concurrency

Some enrichment steps that this service runs are CPU and memory intensive, as they are advanced machine learning steps.

You need to configure the concurrency on the REST enrichment step within your pipeline so you don't send too many concurrent requests. If you do not do this, you will get timeout errors and the items will be marked as ‘error’.

Configuration for this can be found in the Communicating with the Python Rest Service guide. You can perform a short cycle of empirical testing to establish the optimum value for this.