Key takeaways
- Oracle Database 23c introduces AI vector capabilities for enhanced semantic search.
- New features include vector data types, indexes, and search SQL operators.
- Supports Retrieval Augmented Generation without compromising data privacy.
- Improves efficiency of data retrieval processes for various data types.
- Enables natural language queries in applications using LLM-based interfaces.
Oracle recently announced that it plans to add semantic search capabilities using AI vectors to Oracle Database 23c. The new collection comprises new vector data type, vector indexes, and vector search SQL operators, all of which will enable Oracle Database to store and retrieve the semantic content of a wide array of data types, encompassing documents, images, and more, using vectors. This advancement is expected to deliver lightning-fast similarity queries, significantly enhancing the efficiency of data retrieval processes.
Perhaps the most interesting aspect of AI Vector Search is its ability to support Retrieval Augmented Generation (RAG), a leading generative AI technique. RAG combines the power of large language models (LLMs) with sensitive business data to provide accurate responses to natural language queries. Notably, this is accomplished without exposing confidential or private data during the LLM training process, ensuring both data integrity and security.
“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 Oracle Database, we enable customers to quickly and easily get the benefits of artificial intelligence without sacrificing security, data integrity, or performance.” said Juan Loaiza, executive vice president, Mission-Critical Database Technologies, Oracle
Applications built on Oracle Database and Autonomous Database are designed to feature LLM-based natural language interfaces, allowing end-users to query data using everyday language, making data access simple. The company intends to democratise access to natural language processing capabilities for users.
The announcement also encompassed updates to Oracle's suite of products and services. Notably, Oracle Autonomous Database will feature a free container image, allowing developers to create cloud-native applications with the same capabilities as Oracle Cloud Infrastructure (OCI) Always Free Autonomous Database, all while working in an environment that suits their preferences. APEX, Oracle's application development tool, will speed up the development process by converting natural language prompts into SQL queries and introducing integrated workflow and process automation.
Additionally, GoldenGate 23c Free, Oracle's data integration and data mesh solution, will now be accessible for free. This version offers a simplified user experience, making it accessible even to individuals with limited experience.
Two months back in an exclusive interview with AIM, Oracle India’s technology head Saravanan P, had told about their plans to expand into vector databases.
