Oracle Introduces Integrated Vector Database for Generative AI
Vector databases have been all the buzz in the world of Generative AI. Oracle, a giant in the software and cloud computer industry, announced this week its plans to add AI vectors to Oracle Database 23c. The new set of features is called AI Vector Search. It will include vector indexes, vector data types, and vector search SQL operators.
Oracle 23c provides developers access to innovative Oracle Database features to help simplify the development of applications. These capabilities are set to be further enhanced with the introduction of these AI Vector Search. It will help boost developer productivity by allowing them to store and retrieve semantic content, including a variety of data types, such as images, documents, and other unstructured data.
The introduction of an integrated vector database for generative AI will support Retrieval Augmented Generation (RAG), which has emerged as a leading generative AI technique. RAG uses a combination of large language models (LLM) and business data to generate natural language responses. A key benefit of RAG is that it provides high accuracy and avoids exposing private or confidential data such as its LLM training data.
According to Juan Loazia, executive vice president, Mission-Critical Database Technologies Oracle, adding AI vector search to Oracle Database will enable customers to get all the benefits of AI without sacrificing data integrity, performance, or security. Using Oracle AI Vector Search does not require machine learning expertise, making it suitable for administrators and developers of all technical levels.
Juan Loaiza also said “ Searches on a combination of business and semantic data are easier, faster, and more precise if both types of data are managed by a single database. By adding AI Vector Search to the Oracle Database, we enable customers to quickly and easily get the benefits of artificial intelligence without sacrificing security, data integrity, or performance. Using Oracle AI Vector search does not require machine learning expertise. All database users, including developers and administrators, can learn to use it in less than 30 minutes.”
Oracle Database tools such as SL Developer and APEX will be enhanced by generative AI tools to enable developers to use natural language to generate SQL queries and applications without needing to code. In addition, developers will be able to generate complete applications combining AI Vector Search with Oracle’s existing low-code APEX development framework.
Oracle APEX (Oracle Application Express) allows developers to accelerate the process of using AI for rapid application development. It is fully integrated with Oracle Database and with the introduction of Vector AI search, the capabilities of Oracle APEX will be further enhanced.
According to Holger Mueller, vice president and principal analyst, Constellation Research, vector search is primarily an Online Transaction Processing (OLTP) feature and it needs reliability, performance, and scalability. He added that vendors like Oracle who have a proven track record of delivering mission-critical OLTP are well positioned to become leaders in this market.
He further added that Oracle’s innate ability to deliver enterprise-class performance is a key capability for the new Vector Search feature. This will help further build the confidence and trust of CxOs for Oracle Database. Oracle has not announced the availability or pricing details for the new feature.