3.1 Core Select AI Concepts

Introduces key Select AI concepts, including prompts, NL2SQL, RAG, AI models, profiles, providers, and agents.

Topics:

• Actions
  
• Natural Language Prompt
  
• NL2SQL
  
• Chatbot
  
• Conversations
  
• Synthetic Data Generation
  
• Retrieval Augmented Generation (RAG)
  
• AI Agent
  
• AI Model
  
• AI Profile
  
• AI Provider
  
• Large Language Model (LLM)
  

3.1.1 Actions

An action in Select AI is a keyword that instructs Select AI to perform different behavior when acting on the prompt. By specifying an action, users can instruct Select AI to process their natural language prompt to generate SQL code, to respond to a chat prompt, narrate the output, display the SQL statement, or explain the SQL code, leveraging the LLMs to efficiently interact with the data within their database environment.

See Use AI Keyword to Enter Prompts for supported Select AI actions.

3.1.2 Natural Language Prompt

A natural language prompt consists of instructions, questions, or input statements expressed in everyday human language (such as English) that guide an LLM's response. Instead of requiring code or specialized syntax, users interact with the LLM by typing sentences or phrases that describe their intent, ask for information, or specify a task.

For example:

• "What is the revenue in the last quarter in each corporate region?"
• "What is our internal corporate policy on parental leave?"
• "Summarize this article."
• "Write an email to a customer apologizing for a delayed shipment."
• "What are the key differences between SQL and NoSQL databases?"

These prompts leverage the model’s understanding of human language to generate useful, contextually relevant outputs. Natural language prompts are central to LLM usability, making advanced AI capabilities accessible to users without technical expertise.

3.1.3 NL2SQL

Natural Language to SQL (NL2SQL) converts natural language questions into SQL statements using generative AI.

Select AI actively uses NL2SQL to interpret user prompts and generate correct, runnable SQL against your Autonomous AI Database or connected external sources. This enables business users ask questions like “Show me last quarter’s revenue by region” and receive accurate SQL queries and results with no SQL expertise.

3.1.4 Chatbot

An AI-powered conversational agent designed to interact with users in natural language, often used for customer service or information retrieval. In the context of Select AI, the Ask Oracle chatbot helps users ask natural language questions and receive AI-generated responses backed by their database and private content. Through this UI, users can:

• Ask natural language questions and get SQL generated automatically (NL2SQL).
• Run queries against database tables and views using Select AI.
• Use Retrieval-Augmented Generation (RAG) to include private document content stored in Autonomous AI Database.
• Interact with agent teams you defined with Select AI Agent.

See Ask Oracle for more details.

3.1.5 Conversations

Conversations in Select AI represent an interactive exchange between the user and the system, enabling users to query or interact with the database through a series of natural language prompts. Select AI incorporates session-based short-term conversations to generate context-aware responses for the current prompt based on prior interactions. Up to 10 previous prompts are incorporated into the current request with short-term conversations, creating an augmented prompt that is sent to the LLM. Select AI supports using customizable long-term conversations enabling you to use Select AI with different topics without mixing context, that can be configured through conversation APIs from the DBMS_CLOUD_AI Package. See Select AI Conversations.

3.1.6 Synthetic Data Generation

In the context of Select AI, Synthetic Data Generation is the capability to automatically generate artificial data that conforms to your database schema enabling you to populate tables for development, testing, training, or proof-of-concept scenarios without using sensitive or production data. Select AI provides the PL/SQL function DBMS_CLOUD_AI.GENERATE_SYNTHETIC_DATA to produce synthetic data sets. See Synthetic Data Generation for more details.

3.1.7 Retrieval Augmented Generation (RAG)

Retrieval Augmented Generation (RAG) is a technique that involves retrieving relevant information for a user's query and supplying that information to a large language model (LLM) to improve responses and reduce hallucination.

Most commonly, RAG involves vector search, but more generally, includes augmenting a prompt of database content (either manually or automatically) such as schema metadata for SQL generation or database content explicitly queried. Other forms of augmentation can involve technologies such as graph analytics and traditional machine learning.

3.1.8 AI Agent

See Select AI Agent Framework Concepts.

3.1.9 AI Model

A general term encompassing various types of artificial intelligence models, including large language models (LLMs) and transformers (also referred as embedding models), used for tasks like text generation, translation, and image recognition. An AI model is a program, trained on data, that detects patterns and makes predictions or decisions based on new inputs. Within the context of Oracle, AI model specifically refers to the various machine learning and large language models (LLMs) available through Oracle's services. See Concepts for Generative AI for more information.

3.1.10 AI Profile

An AI profile is a specification that includes the AI provider to use and other details regarding metadata and database objects required for generating responses to natural language prompts. See CREATE_PROFILE Procedure and Profile Attributes.

3.1.11 AI Provider

An AI Provider in Select AI refers to the service provider that supplies the LLM or transformer or both for processing and generating responses to natural language prompts. These providers offer models that can interpret and convert natural language for the use cases highlighted under the LLM concept. See Select your AI Provider and LLMs for the supported providers.

3.1.12 Large Language Model (LLM)

A Large Language Model (LLM) refers to an advanced type of artificial intelligence model that is trained on massive amounts of text data to support a range of use cases depending on their training data. This includes understanding and generating human-like language as well as software code and database queries. These models are capable of performing a wide range of natural language processing tasks, including text generation, translation, summarization, question answering, sentiment analysis, and more. LLMs are typically based on sophisticated deep learning neural network models that learn patterns, context, and semantics from the input data, enabling them to generate coherent and contextually relevant text.