SAP AI Core

SAP AI Core is a product on SAP BTP to confidently deploy and manage AI models that natively integrate with SAP applications. It's the foundational layer of AI in SAP BTP.

To get your first hands-on experience with SAP AI Core, complete our tutorial for beginners and read this blog series by the SAP Business AI team.

Execute pipelines
Execute pipelines as a batch job, for example, to preprocess or train your models, or perform batch inference.

Serve inference requests
Deploy а trained machine learning model as a Web service to serve inference requests of trained models with high performance.

Benefit from multitenancy support
Use this service in tenant-aware applications. Implement multi-tenant services to segregate your AI assets and executions to isolate your tenants within SAP AI Core.

Integrate your cloud infrastructure
Register your Docker registry, synchronize your AI content from your git repository, and register your object store for training data and trained models. Productize your AI content and expose it as a service to consumers in the SAP BTP marketplace.

With the generative AI hub in SAP AI Core and SAP AI Launchpad, developers can develop, deploy, and manage custom-built AI solutions and AI-powered extensions of SAP applications.

Get flexible access to broadest range of models & compute capacity
Speed up AI development with access to the broadest set of frontier AI models, infrastructure and tooling.

Extend SAP applications with AI & build custom AI solutions
Combine AI models with your unique data to build powerful custom AI solutions or extend SAP applications.

Safeguard your data & develop AI responsibly
Safeguard your data and maintain full control of your AI lifecycle with SAP‘s trusted privacy and security policies, and a centralized orchestration approach.

Learn more
Read the introduction blog post
Read the documentation
Start the learning journey
Explore the reference architecture

Keen to learn more about how the document grounding capability in generative AI hub will streamline the development of custom AI applications? Read this blog post.

Learning Journey
Embed AI into SAP solutions, configure SAP AI Core and SAP AI Launchpad, train an AI model and serve an AI model.
Start now

Developer Tutorials
To dive deeper into SAP AI Core features, check out the SAP Developers tutorials.

Libraries and SDKs
To increase developer efficiency, SAP AI Core offers multiple libraries and SDKs.

Missions
Build custom AI solutions with our SAP Discovery Center missions.

Using the SAP BTP GenAI Starter Kit, let's simplify the setup of critical infrastructure components like SAP AI Core and SAP HANA Cloud.

Get a comprehensive overview of how to leverage SAP BTP to implement Retrieval Augmented Generation (RAG) applications, along with techniques to enhance results tailored to your use case.

"AI agents" have quickly become one of the most exciting topics in technology, sparking interest across industries. In this session, we'll break down what AI agents really are, trying to bring some clarity to the concept while diving into their transformative potential.

More than just theory, we'll walk you through practical steps for building and implementing agents using the SAP Generative AI Hub. Whether you're new to AI or looking for practical insights, this session will give you the tools to start using AI agents today.

Knowledge Graph RAG or also called GraphRag is a Retrieval Augmented Generation method that uses Knowledge Graphs to ground LLM requests. This leads to improvements in domain specific context and knowledge for LLM requests.

In this session, you will learn how to implement a GraphRAG use case with Generative AI Hub and SAP BTP.

Streamlining GenAI development is crucial for staying ahead in today's competitive landscape. Amazon Bedrock, Generative AI Hub, and SAP BTP offer a powerful synergy that simplifies the entire process, from building to integrating and optimizing GenAI applications.

This session explores the seamless interoperability of these tools, showcasing their benefits in terms of model options, performance, and cost optimization. Gain insights from real-world demos and learn how other customers are leveraging this integrated approach to accelerate their GenAI initiatives.

Orchestration combines content generation with a set of functions that are often required in business AI scenarios. Functions include:

• Templating, which lets you compose a prompt with placeholders that are filled during inference
• Content filtering, which lets you restrict the type of content that is passed to and received from a generative AI model