AI Vector Search

Easily bring the power of similarity search to your business data without having to manage and integrate multiple databases. AI Vector Search enables you to search structured and unstructured data based on its semantics or meaning, in addition to its values. Native vector capabilities can help large language models (LLMs) deliver more-accurate and contextually relevant results with retrieval-augmented generation (RAG).

Oracle Vector Search: Powering the Modern Enterprise (2:43)
Announcing Oracle Database 23ai: Bring AI to your data

Larry Ellison and Juan Loaiza discuss the GenAI strategy behind Oracle Database 23ai.

  • The simplicity of a single database

    Easily combine similarity search with relational, text, JSON, spatial, and graph data types to enhance your apps—all in a single database.

  • Converse in natural language with business data

    Enable natural language search across your private business data using RAG to guide the LLM of your choice.

  • Develop AI apps your way

    Use your favorite development tools, AI frameworks, and languages to build AI apps.

  • AI built for enterprise

    Build mission-critical AI apps with ease. Leverage industrial-strength capabilities to achieve scalability, performance, high availability, and security.

Announcing General Availability: AI Vector Search

Ready to level up your AppDev experience? Leverage the latest AI Vector Search capabilities with Oracle Database 23ai. Learn how to get started today.

The future of data and AppDev

Oracle introduced an integrated vector database to augment generative AI and dramatically increase developer productivity at CloudWorld 2023.

Demo: Accelerate semantic search with AI Vector Search

Learn how AI Vector Search in Oracle Database 23ai combines semantic and business data for faster, more accurate, and more secure results.

Key features of AI Vector Search

VECTOR data type

Use the new native VECTOR data type to store vectors directly in Oracle Database 23ai. Simplify applications by supporting vectors with different dimension counts and formats.

Flexible vector generation

Import embedding models of your choice using the ONNX framework and use them to generate vectors for your data. Optionally import vectors directly into the database.

Vector indexes

Accelerate similarity searches using vector indexes, such as the in-memory neighbor graph index for high accuracy and maximum performance and neighbor partition indexes for massive data sets.

SQL extensions for querying vectors

Use simple, intuitive extensions to SQL for similarity search on vectors within sophisticated queries on relational, text, JSON, and other data types.

Simple target accuracy specification

Specify target search accuracy instead of using obscure, low-level, index-specific parameters. Define default accuracy during index creation and override in search queries if needed.

Exadata optimizations

Accelerate vector index creation and search with Exadata System Software 24ai optimizations. Gain the high performance, scale, and availability Exadata provides to enterprise databases.

RAG uses the results of similarity search to improve the accuracy and contextual relevance of large language model responses to questions about business data. RAG helps identify contextually relevant private data that the LLM may not have been trained on and then uses it to augment user prompts so LLMs can respond with greater accuracy.

The desire to get higher quality answers from LLMs is universal, spanning many industries. Some examples of using RAG for improved accuracy include the following:

  • Chatbots for internal and external users
  • Document searches and summaries
  • Language to code synthesis
  • Answers to questions that require specialized, domain-specific knowledge

RAG helps organizations provide customized answers to business questions without the high cost of retraining or fine-tuning the LLMs.

Retrieval augmented generation diagram, description below
  1. A chatbot enables a dialog with an LLM.
  2. Run similarity search on your private business data and pass those facts to the LLM.
  3. The results are formatted as a prompt and context for the LLM.
  4. The LMM receives up to date business data inputs thereby reducing hallucinations.
  5. The high-quality responses are returned to the chatbot.

May 2, 2024

Oracle Announces General Availability of AI Vector Search in Oracle Database 23ai

Doug Hood, Product Manager, Oracle

Oracle AI Vector Search is a novel capability that allows users to search data based on the semantics, or meaning, of data. The feature enables a new class of applications by enhancing traditional business search with semantic search. The feature allows you to generate, store, index, and query vector embeddings along with other business data, using the full power of SQL.

Read the complete post

Get started with AI Vector Search

Try 20+ Always Free cloud services, with a 30-day trial for even more

Oracle offers a Free Tier with no time limits on more than 20 services such as Autonomous Database, Arm Compute, and Storage, as well as US$300 in free credits to try additional cloud services. Get the details and sign up for your free account today.

  • What’s included with Oracle Cloud Free Tier?

    • 2 Autonomous Databases, 20 GB each
    • AMD and Arm Compute VMs
    • 200 GB total block storage
    • 10 GB object storage
    • 10 TB outbound data transfer per month
    • 10+ more Always Free services
    • US$300 in free credits for 30 days for even more

Learn more about AI Vector Search

With AI Vector Search in Oracle Database 23ai, organizations can combine semantic search of their business data with relational queries inside the same database.

Contact sales

Interested in learning more about Oracle AI Vector Search? Let one of our experts help.

  • They can answer questions like:

    • How can Oracle AI Vector search help my business?
    • How can I leverage OCI to run my Oracle Database workloads?
    • How can I get the most out of my Oracle investments?