In the domain of generative AI models, characterized by the impressive capabilities of Large Language Models (LLMs), a notable limitation persists. These models lack access to company-specific or recent data beyond their initial training set. In a groundbreaking announcement at the 2023 TechEd, SAP revealed a strategic solution set to launch in Q1 of 2024: the SAP HANA Cloud Vector Engine. This innovative product aims to bridge the gap by integrating the potency of generative AI with organization-specific data, which is a form of the revolutionary technique known as Retrieval Augmented Generation (RAG).
THE VECTOR ENGINE EXPLAINED
At the core of the Vector Engine’s functionality are ‘embedding functions,’ instrumental in transforming unstructured data objects, ranging from text to images and audio, into high-dimensional vector embeddings. Picture these vectors as pointers within a high-dimensional space; each dimension marked by a numerical data point. The conversion of data objects into numerical representations facilitates the retention of semantic similarities between them. Consequently, the Vector Engine empowers users to assess the extent of similarity between two objects by identifying the distance within this high-dimensional space, providing valuable insights, such as identifying words with analogous meanings.
The Vector Engine seamlessly integrates with SAP HANA database tables, allowing its use in various machine learning and data analytics tasks through simple SQL statements. The vector embeddings are stored in a field of the type REAL_VECTOR, containing the numerical representation of each dimension. Leveraging the built-in COSINE_SIMILARITY function, users gain the ability to effortlessly identify the nearest neighbour of an object, based on the cosine of the angle between their vectors.
FROM THEORY TO PRACTICE
As the concept may seem somewhat abstract, let’s delve into a practical example to illustrate how developers can leverage the Vector Engine to enhance business outcomes. Imagine a retail scenario where the Vector Engine is applied to enhance customer engagement. By storing customer reviews, purchase history, and feedback into high-dimensional vectors, the Vector Engine allows businesses to identify similar sentiments or preferences. This facilitates personalized recommendations, ultimately refining the customer experience. Moreover, when combined with generative AI, it opens the door for personalized customer-support, targeted marketing texts, and more.
An alternative use-case could involve storing system documentation as vector embeddings and utilizing them as context when employing AI for developmental assistance. This approach even allows you to ask specific questions about your system documentation. Of course these are only some of the potential use-cases and only time will reveal the full spectrum of purposes for which this technique will prove most useful.
EMBRACING A PROMISING FUTURE
In essence, SAP’s HANA Cloud Vector Engine signifies a new era by unlocking the potential of company-specific data within the realm of generative AI. As we anticipate its launch in Q1 of 2024, the Vector Engine promises to revolutionize how businesses harness the capabilities of AI models, introducing a paradigm shift towards more contextually appropriate results and setting the stage for unprecedented advancements in the field.
Curious to explore more about the Vector Engine and how you can leverage it to optimize your business results? Feel free to contact us! You can also follow us on LinkedIn to stay updated on the latest developments related to AI and other SAP technologies.
For an overall recap on the SAP TechEd 2023, check out our latest blog: SAP TECHED RECAP – EXPLORING BTP AND AI.