About felixbartler

felixbartler

When deploying machine learning models on SAP AI Core, they are exposed at a deployment URL for consumption. In this blogpost we will look into easy options to make these endpoints static, so that you have a easy time to integrate them to into applic...

felixbartler

Welcome to this deep-dive blog series about SAP AI Core template creation. In this series of blogs, I will show some of the details of the WorkflowTemplate and ServingTemplate concept by concept. This blog will focus on ways of using environment vari...

felixbartler

SAP AI Core is the AI Workload Management Solution on SAP BTP. Its the place to be for Machine Learning Engineers in the SAP domain and brings a bunch of out-of the box features supporting in training and serving machine learning scenarios. To streng...

felixbartler

In this brief blog post, I want to share an issue I've encountered multiple times with SAP AI Core. While packaging my Docker container using a standard Dockerfile, Python scripts, and execution commands, everything seemed fine locally. However, I en...

felixbartler · 01-15-2024

Custom Python operators in SAP Data Intelligence stand out as a versatile tool for developing bespoke integrations. The richness of Python's library ecosystem opens up endless opportunities. This article will delve into how pyodbc, as a robust and ve...

felixbartler

@ClaudiusHantke HANA DB would require TCP.

felixbartler · 01-12-2024

Hello Weikun Liu, this specific error I did not encounter before, but I can give you a general overview of these kind of cuda issues from my experience: The CUDA base image version needs to be compatible with the installed CUDA driver (see my ot...

felixbartler · 01-09-2024

Okay, looks good, is the host behind the red box the same thing you can see in the BTP Cockpit under Cloudconnectors? (Under Exposed-Backends see the 2. Screenshot). By the way you can also just send me an email to my work address and we figure it ou...

felixbartler · 01-09-2024

Yes so be careful: 1. screenshot from cloud connector - there we use TCP - 3. Screenshot DI Connection Management (here we just use HTTP as a "dummy" - does not have anything to do with it really. We only need a connection type that supports the clou...

felixbartler · 01-09-2024

Hi John, in step 1 you see the cloud connector configuration, it actually needs to be a TCP configuration. (Not HTTP). Maybe if they are finished you can take a screenshot and send that over, then we can have a look together. Best Regards, Felix

User Statistics

User Activity

SAP AI Core Static Deployment URL

SAP AI Core Templating: Environment Variables

CI/CD with SAP AI Core

SAP AI Core Dockerfiles: Fixing Permission denied: '/nonexistent'

SAP Data Intelligence Python Operators with pyodbc

Re: SAP AI Core and the Cloud Connector: Overview and Technical Deep Dive

Re: Running Language Models – Deploy Llama2 7b on AI Core

Re: Proxy Third-Party Python Library Traffic - Using SAP Cloud Connector in SAP Data Intelligence Python Operators

Re: Proxy Third-Party Python Library Traffic - Using SAP Cloud Connector in SAP Data Intelligence Python Operators

Re: Proxy Third-Party Python Library Traffic - Using SAP Cloud Connector in SAP Data Intelligence Python Operators