SAP is going full speed with AI agents on Joule. Indeed, it's incredible how such agents can address complex requests by orchestrating a set of generic tools they are given access to.If you have a need to build your own custom AI agent on BTP, then t...
If you have a collection of FAQs that you want to be easily accessible for your business users, then an assistant that is powered by a Large Language model might be part of the answer.This blog explains how to create such a backend (REST-API), that c...
SAP Datasphere is a comprehensive data orchestration platform, with a graphical user interface that also addresses less technical business users. SAP HANA Cloud is embedded into SAP Datasphere, which gives SAP Datasphere access to its multi-model cap...
Since SAP HANA Cloud is a multi-model database management system, it can store, process and enrich different kinds of data (ie tables, geo-spatial, graph) with its in-built engines. This blog shows how to implement a SAP Business AI project with a ti...
If you have a collection of FAQs that you want to be easily accessible for your business users, then a chatbot might be the answer. This blog explains how to create such a (non-hallucinating) chatbot on SAP's Business Technology Platform by leveragin...
That's great, happy that it's working now. Can you please check whether BIGINT works in the latest hana_ml version. (currently 2.23.25021400). Our Product Group can then check whether this is an issue with the algorithm or the documentation.
Hi @mark_foerster The error "Input table 0: column 0 has invalid SQL type" typically means that one of of the columns has a type that is not supported by the algorithm. Here in the first table the first column.The supported column types of the PAL al...
@AdrianDBorja Let me try to reach out to our Product Group on the error you are getting.Just to double check though, the hands-on example in this blog is working for you. Your question is about applying the same concept on your own data?In the meanti...
Hello @AdrianDBorja , Thanks for the feedback.For 1) massive=True allows to train multiple time series forecast with a single command. In the blog it is used in combination with the group_key to forecast indidvidual values for each country. Maybe you...
Hi @Moritz_F, the Python operator in a Datasphere Data Flow supports only the Python packages listed here. Further packages cannot be installed. Please also consider that the Python operator receives the data in packages. You are not guaranteed to ge...