Autonomous Database Select AI

Use natural language to analyze your data and get quick insights about your business—no matter where the data is stored.

Use natural language to query data in Autonomous Database (1:39)
Announcing generative development (GenDev) for enterprise

Watch the replay of EVP Juan Loaiza’s Oracle CloudWorld keynote to learn about this groundbreaking, AI-centric AppDev infrastructure.

Why Autonomous Database Select AI?

  • Analysts get quick answers to their questions

    Get rapid new insights from all your data via natural language conversations assisted by retrieval-augmented generation—without performing complex manual processes or waiting for IT’s help. Select AI also enables Oracle E-Business Suite users ask questions in their natural language and get results about their business through the Ask Oracle E-Business Suite chat app.

  • Developers deliver apps with built-in AI

    Easily enhance existing apps or develop new ones with a built-in natural language question-to-SQL query capability in a conversational thread using LLMs over structured and unstructured data. Automate the population of your vector data in Autonomous Database with your content and enable RAG for semantic similarity search.

  • IT helps accelerate AI innovation

    Enable your stakeholders to use a choice of LLMs from Cohere AI, Azure OpenAI, OpenAI, and OCI Generative AI to securely interact with data using natural language. No integrations or cumbersome manual operations required.

Converse with your data diagram, description below

The image shows how Autonomous Database Select AI works. The diagram outlines how you can have a conversation with your data by asking a natural language question through an interface, such as an integrated development environment or application, via text or voice.

Autonomous Database Select AI then uses a large language model (LLM) to generate a SQL query and performs the following tasks:

  • 1) Augments the natural language question with metadata from the schema(s) identified in the user’s profile.
  • 2) Feeds the LLM with an augmented prompt.
  • 3) LLM produces a SQL query against the database.
  • 4) Query is run and the result is sent to the user.
  • 5) Previous questions are retained for conversation-like user interactions.

Finally, the user receives a response back with the answer from their own organization’s data, based on its existing data security policy.

Generate targeted personalized content diagram, description below

This image shows how Autonomous Database Select AI works. The diagram shows how you generate personalized content just by asking a question into the Select AI prompt.

A user kicks off a workflow through an application. For example, the user wants to create a promotional offer based on a customer’s previous purchases.

The application utilizes data in Autonomous Database and creates personalized targeted promotional offers via a large language model (LLM) including these steps:

  • 1) Context from Autonomous Database (for example, customer demographic info and purchasing behavior, products that need to be promoted, etc.) is queried.
  • 2) Prompt task instructions are combined with this data (for example, recommend similar products from the promoted product list; write a personalized and convincing e-mail with the recommendations)
  • 3) It then feeds the LLM with the augmented prompt and processes the result.

The final output is provided to the user that includes a compelling promotional email offer with personalized product recommendations based on customer information, behavior and past purchases.

Build automated AI pipeline content diagram, description below

The image shows how Autonomous Database Select AI works. The diagram outlines how you can build automate the creation and population of vector store from text files such as, txt and html, on your object store.

Select AI automatically processes documents to chunks, generates embeddings, stores them in the specified vector store, and updates the vector index as new data arrives:

  • 1) Input: Data is initially stored in an object storage.
  • 2) Autonomous Database retrieves the input data or the document, chunks it, and passes to an embedding model.
  • 3) The embedding model processes the chunk data and returns vector embeddings.
  • 4) Output: The vector embeddings are stored in Autonomous Database as a vector data type for use with RAG. As content is added, the vector index is automatically updated.
Enable retrieval-augmented generation (RAG) content diagram, description below

The image shows how Autonomous Database Select AI works. The diagram outlines how Select AI implements retrieval-augmented generation (RAG).

RAG retrieves relevant pieces of information from the enterprise database to answer a user's question. This information is provided to the specified large language model along with the user prompt. Select AI uses this additional enterprise information to enhance the prompt, improving the LLM's response. RAG can enhance response quality with update-to-date enterprise information from the vector store:

  • 1) Input: User asks a question.
  • 2) Autonomous Database Select AI generates vector embeddings of the prompt using the embedding model specified in the AI profile.
  • 3) Autonomous Database Select AI uses the generated embedding and AI Vector Search to find similar content from the customer’s enterprise data.
  • 4) The vector search returns the top K results which will be used to augment the prompt.
  • 5) Autonomous Database sends the top K query results with user question to the LLM.
  • 6) The LLM returns its response to the Autonomous Database instance.
  • 7) Output: Autonomous Database Select AI provides the response to the user

Industry analyst reviews of Autonomous Database Select AI

  • IDC logo

    “With Autonomous Database giving users an enterprise view of an organization’s data and Select AI providing a natural language interface with wide-ranging SQL translation and generation capabilities, you have a differentiated combination that pushes the boundaries of data interaction to new levels.”

    Carl Olofson
    Research Vice President, Data Management Software, IDC
  • The Futurum Group logo

    "With Select AI, Oracle is first to market with a generally available capability for organizations to have a contextual dialogue with their private, proprietary data—intuitively. It’s so simple that organizations of all sizes can use it immediately, placing Autonomous Database with generative AI at the forefront of data platform innovations.”

    Ron Westfall
    Senior Analyst and Research Director, The Futurum Group
  • NAND Research logo

    “With support for a broad range of LLMs, and the ability for everyone from developers to project managers to now easily hold a conversation with their troves of corporate data and obtain instantaneous insights instead of writing SQL queries or asking someone else in their organization for help, Oracle’s Autonomous Database Select AI clearly elevates the productivity of organizations that adopt it.”

    Steve McDowell
    Chief Analyst & CEO, NAND Research
  • Omdia logo

    “Technically speaking, Autonomous Database with Select AI is a really cool innovation. The ability for anyone to converse with enterprise data not in SQL but instead in their own language will do wonders for employee productivity since no coding or database gymnastics are required to use Oracle's smart implementation.”

    Bradley Shimmin
    Chief Analyst, AI Platforms, Analytics, & Data Management, Omdia
September 10, 2024

Announcing Select AI with Retrieval-Augmented Generation (RAG) on Autonomous Database

Mark Hornick, Senior Director, Data Science and Machine Learning, Oracle

Select AI’s new support for retrieval-augmented generation (RAG) makes it easy to use large language models (LLMs) to gain insight or generate innovative content based on your private data using natural language prompts. Use Select AI with RAG to get more relevant responses to your natural language questions while helping reduce the risk of hallucination.

Get started with Autonomous Database Select AI

Get Autonomous Database for free

Oracle Cloud Free Tier offers more than 20 services, such as compute, storage, and Autonomous Database, that you can use for an unlimited time. You’ll also receive a US$300 cloud credit to use within 30 days to try additional cloud services. Get the details and sign up 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