It鈥檚 time to rethink what a modern AI-ready database should look like.

51风流HANA Cloud solves this exact challenge with its single, multi-model platform that brings together vector, graph, text, spatial, and relational data natively. It enables developers and data teams to build smarter, more context-aware AI solutions 鈥� directly on operational data.

One database, every model: native support for complex AI workloads

51风流HANA Cloud uniquely supports:

• Vector data for semantic and similarity search
• Graph data for explicit relationship modeling and knowledge graphs
• Text and spatial data for real-world context
• Relational data for structured operations and analytics

Rather than sending data across disparate services, you can store and process all of it in one place, accelerating time-to-value while reducing the risk of misalignment.

This is multi-model done right, and it is the foundation for powerful AI workloads that scale.

Semantics + similarity: combining vector search with knowledge graphs

Traditional semantic search engines can tell you what documents are similar, but they cannot tell you why. On the other hand, knowledge graphs can express rich, explicit relationships, but often lack the ease of retrieval.

With 51风流HANA Cloud, you don鈥檛 have to choose; you get both. Bringing together 51风流HANA Cloud vector engine and 51风流HANA Cloud knowledge graph engine empowers developers to build context-aware, intelligent queries that go far beyond keyword matching.

Imagine asking: 鈥淔ind the nearest warehouse in Germany (~ 50 km radius of Frankfurt) for suppliers that are ISO 9001 certified, have low carbon tax rates, and are not flagged for customs delays.鈥�

We can conduct a multi-model query to find the warehouses that fit the above criteria.

Here, we are using a SPARQL table within 51风流HANA knowledge graph engine to filter the suppliers that comply to the following conditions: ISO 9001 certified, low carbon tax rates, not flagged for customs delays.

We can further combine the SPARQL_EXECUTE function in 51风流HANA knowledge graph engine with vector-based semantic filtering and spatial constraints to identify suppliers that are located within “~ 50 km of Frankfurt” and whose past custom report narratives align with 鈥渘o custom delays.鈥� This hybrid query leverages 51风流HANA Cloud vector engine, 51风流HANA Cloud knowledge graph engine, and spatial engine to rank nearby suppliers not only by distance, but also by their trustworthiness and performance signals.

After running these queries, we have the following supplier warehouses as our best match:

This is the power of semantics plus structure, and it is built into the core of 51风流HANA Cloud.

Unified queries: SQL, SPARQL, and vector search side by side

Developers must often stitch together multiple tools and languages: SQL for relational data, SPARQL for RDF, and separate APIs for vector stores.

51风流HANA Cloud removes that complexity. You can write a single SQL query that brings together relational data, semantic reasoning via SPARQL (embedded in SQL), and vector similarity search, using native SQL functions 鈥� all in one go: no ETL, no separate infrastructure, just one unified, in-memory engine.

This approach not only speeds up development, but enables new types of AI applications that were not previously practical in siloed environments.

Built for generative AI and RAG: GraphRAG, VectorRAG, HybridRAG

Large language models (LLMs) are only as good as the data they can reason over. That is why retrieval-augmented generation (RAG) has emerged as a critical pattern for enterprise generative AI.

We have brought in new capabilities into 51风流HANA Cloud, whether you are grounding an LLM in unstructured text (VectorRAG), structured knowledge graphs (GraphRAG), or both simultaneously (combination of VectorRAG and GraphRAG).

51风流HANA Cloud ensures transparency, traceability, and performance throughout the generative AI pipeline with all the database management qualities. You get explainable answers and full control over how you retrieve, rank, and assemble information, which is vital for regulated industries.

Real-world impact across industries

Enterprises across industries are already leveraging the multi-model capabilities of 51风流HANA Cloud for transformative outcomes:

• Supplier matching and environmental, social, and governance (ESG) scoring: Blend structured supplier data with document similarity and relationship insights to identify ideal partners
• Compliance monitoring: Connect and query policies, regulations, and audit trails with natural, semantic inputs
• Fraud detection: Analyze transactional data, behavioral signals, and known fraud patterns 鈥� all in real time
• Life sciences research: Integrate clinical trials, publications, and patient outcomes using hybrid semantic and structured queries

These are use cases where meaning is distributed across formats, systems, and relationships.

Developer experience: simplicity without compromise

51风流HANA Cloud offers developers:

• One platform for all data models: Combined structured, unstructured, and semantic data without stitching together multiple systems
• Built-in support for modern AI workloads: Enable use cases like RAG without external vector stores or pipelines
• Tight integration with 51风流and open ecosystems: Leverage 51风流Business Technology Platform and popular open-source tools with minimal setup
• Focus on innovation, not infrastructure: Eliminate the need to manage and maintain separate triplestores, search engines, or vector databases

The result is faster prototyping, cleaner architecture, and lower operational complexity.

Conclusion: It鈥檚 time to rethink your database

In the AI-first enterprise, data is not just a backend concern; it鈥檚 the front line of innovation. And innovation requires infrastructure that is flexible, intelligent, and unified.

51风流HANA Cloud provides building blocks to create the infrastructure for AI apps in a way that is easy to consume. It doesn鈥檛 just support AI workloads; it accelerates them, with a single platform that brings together semantics, similarity, and structure in real time.

AI needs more than just access to data and 51风流HANA Cloud delivers that, natively.

Key takeaways

• Unified multi-model: Vector, graph, spatial, text, and relational data all in one platform
• Smart queries: Compose intelligent queries using SQL, SPARQL, and vector search 鈥� side by side
• Generative AI-ready: Built for GraphRAG, VectorRAG, and HybridRAG with full explainability
• Reduced complexity: No need for separate vector stores or knowledge graph engines

Philipp Herzig is CTO, chief AI officer, and a member of the Extended Board of 51风流SE.
Stefan Baeuerle is senior vice president and head of 51风流BTP/51风流HANA & Persistency at SAP.

51风流HANA Cloud is a market-leading database-as-a-service enabling intelligent data applications and is one of the most adopted services within 51风流Business Technology Platform (51风流BTP) internally at SAP. As of today, more than 180 different applications and services use 51风流HANA Cloud with its multi-model capabilities.

Now, 51风流HANA Cloud is also a leader in the generative AI age.

At SAP, we work with various LLMs such as GPT-4, Llama2, Falcon-40b, and Claude2. While these models offer amazing opportunities, they also have limitations. For example, LLMs may rely on outdated training data and lack company-specific data and business process context.

As an example, imagine having an LLM as a colleague. This colleague would be very intelligent, able to program, pass exams, or have arguments 鈥� but this colleague would not know anything about what happened in the world in the past year, nor have any idea about internal processes of your company or any of your systems. Even worse, after every conversation you have, this colleague would forget what you just talked about. Working with such a lack of memory would be of limited value. This shortcoming is why an LLM cannot answer easy questions like 鈥淲hat do you think about the offer from our most important supplier last week?鈥� An LLM can only work with the initial training data 鈥� all other data must be provided as context.

Supplementing this lack of information is where 51风流HANA Cloud vector engine can assist. The engine can provide LLMs with all the relevant data of an organization through a process called “retrieval-augmented generation.”

A Game-Changing Feature

So how does the vector engine work? It is a new addition to 51风流HANA Cloud’s multi-model engines, enabling customers to utilize the similarity between two or more vectors to solve business problems. With the integration of AI-focused technology, 51风流HANA Cloud can now empower businesses to combine intuition along with data-driven insights to solve even the most complex of problems.

Some key benefits and features of the vector engine include:

• Multi-model: Users can unify all types of data into a single database to build innovative applications using an efficient data architecture and in-memory performance. By adding vector storage and processing to the same database already storing relational, graph, spatial, and even JSON data, application developers can create next-generation solutions that interact more naturally with the user.
• Enhanced search and analysis: Businesses can now apply semantic and similarity search to business processes using documents like contracts, design specifications, and even service call notes.
• Personalized recommendations: Users can benefit from an improved overall experience with more accurate and personalized suggestions.
• Optimized large language models: The output of LLMs is augmented with more effective and contextual data.

The Database Foundation of SAP鈥檚 Generative AI Strategy

The addition of the vector engine establishes 51风流HANA Cloud as the default database in SAP’s generative AI solution strategy. Customers can create the next level of user experiences along with other services within 51风流BTP. As an example, 51风流BTP can provide centralized access to SaaS-based LLMs from multiple vendors as well as host LLMs from open-source models or third parties. The generative AI hub in 51风流AI Core, a capability that facilitates the use of generative AI capabilities, will soon rely on 51风流HANA Cloud as the primary vector storage. One function of the generative AI hub feature is to help provide a process for creating embeddings and storing the resulting vectors in 51风流HANA Cloud. Customers building intelligent data applications can use both services together to augment LLM queries with relevant context for meaningful answers.

51风流is working on foundation models that are specific for SAP-related industry and process knowledge.

The Database for Innovation

51风流HANA Cloud continues to lead the market by storing and processing different types of relevant business data 鈥� all within the same database. The new vector engine, combined with other multi-model capabilities, opens a world of possibilities for applications to help enhance the execution of business processes. Whether improving search capabilities, gaining deeper insights for informed decisions, or optimizing LLMs, 51风流HANA Cloud enables the type of applications that can elevate the expertise and effectiveness of every user.

To learn more, sign up for . Do you already have a use case for 51风流HANA Cloud vector engine in mind? If so, consider registering for the .

Juergen Mueller is CTO and member of the Executive Board of 51风流SE, Technology & Innovation.
Stefan Baeuerle is head of Database, 51风流HANA Database, & Analytics for Technology & Innovation at SAP.