About Select AI
Use natural language to interact with your database and LLMs through SQL to enhance user productivity and develop AI-based applications. Select AI simplifies and automates using generative AI, whether generating, running, and explaining SQL from a natural language prompt, using retrieval augmented generation with vector stores, generating synthetic data, or chatting with the LLM.
When you use Select AI, Autonomous Database manages the process of converting natural language into SQL. This means you can provide a natural language prompt instead of SQL code to interact with your data. Select AI serves as a productivity tool for SQL users and developers and enables non-expert SQL users to derive useful insights from their data, without having to understand data structures or technical languages.
Select AI also automates the retrieval augmented generation (RAG) process from generating vector embeddings to retrieving relevant content based on your prompt through semantic similarity search using your vector store. Other features include synthetic data generation, supporting chat history for conversations, and other features, all from a SQL interface.
DBMS_CLOUD_AI
package
enables
integration with a user-specified LLM for generating SQL code using natural language
prompts. For natural language to SQL generation, this package provides an augmented
prompt to the LLM containing the relevant database schema metadata. This enables
generating, running, and explaining SQL queries based on natural language
prompts.
It also facilitates retrieval augmented generation using vector stores, synthetic
data generation, and allows for chatting with the
LLM. The DBMS_CLOUD_AI package works with AI
providers listed in Select your AI Provider and LLMs.
-
You must have an account with the AI provider and provide the credentials through
DBMS_CLOUD_AIobjects that the Autonomous Database uses. -
You can submit prompts in multiple languages. The quality of the result depends on the abilities of the specific LLM or the embedding model (transformer) being used. Check your LLM or embedding model documentation for multi-language support.
Topics
- Usage Guidelines
Provides usage guidelines to assist in the use of Select AI for natural language to SQL generation.. - Supported Platforms
Select AI is supported on Autonomous Database Serverless and Autonomous Database on Dedicated Exadata Infrastructure and Cloud at Customers. - Select your AI Provider and LLMs
Choose an AI provider and LLM that meets your security standards and aligns with your specific needs, like text or code generation.
Usage Guidelines
Provides usage guidelines to assist in the use of Select AI for natural language to SQL generation..
Intended Use
This feature generates, runs, and explains SQL queries from user-provided natural language prompts. It automates tasks that users would otherwise perform manually using their schema metadata and a large language model (LLM) of their choice. Additionally, it facilitates retrieval augmented generation with vector stores and enables chatting with the LLM.
Depending
on the Select AI action you specify, you provide a prompt, whether for natural language
to SQL generation, RAG, or pass-through chat, and Select AI automates the interaction
with LLMs and your database using SQL and PL/SQL interfaces. Specifically, it generates
SQL queries from natural language based on metadata from the specified schema and
tables. Additionally, it facilitates chat-based generative AI, optionally enhanced with
content from vector stores through retrieval augmented generation (RAG) for improved
response quality. It also explains SQL queries based on natural language prompts and
supports synthetic data generation for one or multiple schema tables. Select AI enables
submitting general requests with the chat action.
Prompt Augmentation Data
For SQL query generation, the database augments the user-specified prompt with database metadata to mitigate hallucinations from the LLM. The augmented prompt is then sent to the user-specified LLM to produce the query. When using vector stores with retrieval augmented generation (RAG), content from the vector store is retrieved using semantic similarity search with the provided prompt. This content becomes part of the augmented prompt that is sent to the LLM.
The database augments the prompt with schema metadata only. This metadata may include schema definitions, table and column comments, and content available from the data dictionary. For the purposes of SQL generation, the database does not provide table or view contents (actual row or column values) when augmenting the prompt.
narrate action, however, does provide to the LLM
either:
- the result of a natural language to SQL query, which contains database data, or
- the result of semantic similarity search as retrieved from the vector store supporting retrieval augmented generation (RAG).
WARNING:
Large language models (LLMs) have been trained on a broad set of text documentation and content, typically from the Internet. As a result, LLMs may have incorporated patterns from invalid or malicious content, including SQL injection. Thus, while LLMs are adept at generating useful and relevant content, they also can generate incorrect and false information including SQL queries that produce inaccurate results and/or compromise security of your data.
The queries generated on your behalf by the user-specified LLM provider will be run in your database. Your use of this feature is solely at your own risk, and, notwithstanding any other terms and conditions related to the services provided by Oracle, constitutes your acceptance of that risk and express exclusion of Oracle’s responsibility or liability for any damages resulting from that use.
Parent topic: About Select AI
Supported Platforms
Select AI is supported on Autonomous Database Serverless and Autonomous Database on Dedicated Exadata Infrastructure and Cloud at Customers.
- Autonomous Database Serverless
- Autonomous Database on Dedicated Exadata Infrastructure
- Autonomous Database on Dedicated Exadata Infrastructure Region
- Autonomous Database Cloud@Customer
Parent topic: About Select AI
Select your AI Provider and LLMs
Choose an AI provider and LLM that meets your security standards and aligns with your specific needs, like text or code generation.
Different LLMs excel at various tasks based on their training data and intended purpose. Some models are excellent for text generation but may not perform well in code generation, while others are specifically optimized for coding tasks. Choose an LLM that best suits your needs.
| AI Provider | LLMs | Embedding Model for RAG | Purpose |
|---|---|---|---|
|
OCI Generative AI |
|
|
The OCI Generative AI Chat models are supported for
all The OCI Generate text models are supported only for
Note
For models that accept images,
use The meta.llama-3.2-90b-vision-instruct model is specifically trained for vision and images. While it can be used for text and SQL generation, the model is best suited for images. For more details, see Profile Attributes. |
|
Azure OpenAI Service |
|
text-embedding-ada-002 |
Best suited for generating SQL from natural language
prompts, |
|
OpenAI |
|
text-embedding-ada-002 |
Best suited for generating SQL from natural language
prompts, |
|
Cohere |
|
embed-english-v2.0 |
Best suited for |
|
|
|
text-embedding-004 (default) |
Best suited for generating SQL from natural language
prompts, |
|
Anthropic |
|
NA |
Best suited for generating SQL from
natural language prompts, |
|
Hugging Face |
|
NA |
Best suited for generating SQL from
natural language prompts, |
Embedding models are also known as transformer models.
Parent topic: About Select AI