Training Failed error when training a similarity model in Predictive Intelligence

[boyan_kushlev]

I have a simple developer instance I requested from ServiceNow Developers a month ago. I want to use Predictive Intelligence to train a model on the existing knowledgebase articles in the database so that I can show related articles based on the current article's content. I installed the Predictive Intelligence plugin along with its dependencies.

When I go to Predictive Intelligence > Similarity > Solution Definitions and click on the Knowledge Similar Articles definition, I can see there are 1200 matching records from the kb_knowledge table. Fields are set to Short Description, Article Body, Wiki, and test fields - to Short Description. These are the default values. When I click on Update & Retrain at the bottom I can a training is scheduled in the Training Request Schedules tab. When I click on it and then click on Execute Now, and then go to the ML Solutions tab, I can see the state of the solution is showing "Configuration OR Network Error" (see attachment). I can keep retraining it, changing values, etc, etc, and all I get is this error. Once I retrain it, the previous solution would go to either "Training request timed out" or "Training is canceled".

I have no idea what is causing this issue. I found other people having a similar issue, but no resolutions whatsoever. Some respondents mentioned Predictive Intelligence doesn't work on personal developer instances, but this doesn't make a lot of sense - why is it on the plugin store in the first place? And if that's actually the case, what can I do to use it? Should I request a different type of instance? The documentation doesn't say anything about that.

[Lener Pacania1]

Hi Boyan,

Unfortunately, I think at this time the PDI's do not support training.  I spun up a Paris PDI and an Orlando PDI last night using a personal e-mail to test and was also unable to train. I have a request into product management to check if PDI's will support training in the near future.  

So, until we get this resolved you have a couple options:

1. If you have a ServiceNow sub-prod instance you can train and predict there.

2. Or if you are trying to learn about the Predictive Intelligence capabilities you can register for the free K20 "Accelerate Incident Resolution with Predictive Intelligence and Agent Workspace" class on https://nowlearning.service-now.com.  Once you enroll this K20 class will spin up an instance for 3 days which is configured so that you can run training & predictions.  You have admin rights to this temporary instance so you can also load you own data if desired.  The lab instance does have a good amount of incident data already in it.

I'm putting the training error from my PDI's as reference for product management.

Best, Lener

[Kalyani Undadi]

Hi @Lener Pacania ,

Is the error "Training request timed out" is solved. If yes please help me how that can be solved.

Best Regards,

Kalyani Undadi

[Lener Pacania1]

Hi Kalyani, if the error is on a PDI then you can't use Predictive Intelligence on it.  If you are getting the error on a sub-prod or prod instance open a Hi ticket and support can help you resolve the time out issue.  -Lener

[Kalyani Undadi]

Hi Lener,

Its working fine in DEV Instance but we are facing this issue in QA for the same Solution definition. Will open a HI ticket. Thanks for your response.

Best Regards,

Kalyani Undadi

[geethuarul]

Hi Kalyani Undadi,

Can we train ML models in Developer instance? I am getting an error while training the models.