Oracle Announces HeatWave GenAI, Featuring In-Database LLMs, Automated Vector Store

Oracle has announced the general availability of HeatWave GenAI, which includes in-database large language models, an automated in-database vector store, scale-out vector processing and the ability to have contextual conversations in natural language informed by unstructured content.

These capabilities will enable enterprises to leverage generative artificial intelligence for their data without requiring AI expertise or moving data to a separate vector database, Oracle said in a press release. HeatWave GenAI is available in all Oracle Cloud regions, Oracle Cloud Infrastructure Dedicated Region and across clouds.

With HeatWave GenAI, developers can create a vector store for enterprise unstructured content with a single SQL command, using built-in embedding models, the company said. Users can perform natural language searches using in-database or external LLMs. Data doesn’t leave the database, and there is no need to provision GPUs. As a result, developers can reduce application complexity, increase performance, improve data security and lower costs.

According to Oracle, new features of HeatWave GenAI include:

• In-Database LLMs: These simplify the development of generative AI applications without the need for external LLM selection and integration, and availability of LLMs in cloud providers’ data centres. The in-database LLMs enable customers to search data, generate or summarise content, and perform retrieval-augmented generation with HeatWave Vector Store. They can combine generative AI with other built-in HeatWave capabilities such as AutoML to build applications. HeatWave GenAI is also integrated with the OCI Generative AI service to access pre-trained, foundational models from LLM providers.

• Automated In-Database Vector Store: The vector store enables enterprises to use generative AI with their business documents without moving data to a separate vector database and without AI expertise. Steps to create a vector store and embeddings are automated and executed inside the database. Using a vector store for RAG helps solve the hallucination challenge of LLMs as the models can search proprietary data with appropriate context to provide relevant answers.

• Scale-Out Vector Processing: HeatWave supports a new, native Vector data type and an optimised implementation of the distance function, enabling customers to perform semantic queries with standard SQL. In-memory hybrid columnar representation and scale-out architecture enable vector processing to execute at near-memory bandwidth and parallelise across up to 512 HeatWave nodes, which helps in getting answers to queries faster.

• HeatWave Chat: This is a Visual Code plug-in for MySQL Shell, which provides a graphical interface for HeatWave GenAI and enables developers to ask questions in natural language or SQL. The integrated Lakehouse Navigator enables users to select files from object storage and create a vector store. HeatWave maintains context with the history of questions asked, citations of the source documents and the prompt to the LLM. This facilitates a contextual conversation and allows users to verify the source of answers generated by the LLM.

“Today’s integrated and automated AI enhancements allow developers to build rich generative AI applications faster, without requiring AI expertise or moving data. Users now have an intuitive way to interact with their enterprise data and rapidly get the accurate answers they need for their businesses,” said Edward Screven, chief corporate architect at Oracle.