GENERATE SQL - Kinetica Docs

Parameters

Natural-language question for which an equivalent SQL query will be generated

Name of the schema containing the context to use in generating the query

WITH OPTIONS

Optional indicator that a comma-delimited list of SQL generation option/value assignments will follow.See SQL Generation Options for the complete list of options.

SQL Generation Options

The following options can be specified to modify the way SQL queries are generated.

ai_api_provider

Name of an LLM service to use other than the default one; the default, sqlgpt, uses the Kinetica SQLGPT.io service.

ai_api_url

URL of an LLM service to use other than the default one.

context_name

Name of the SQL-GPT context to use as a basis for generating SQL queries; should be of the form [<schema name>.]<context name>.

context_names

Comma-separated list of names of SQL-GPT contexts to use as a basis for generating SQL queries; each should be of the form [<schema name>.]<context name>, and the entire list should be single-quoted.For example:

context_names = 'example.atc_ctx,example.nyctaxi'

use_rag

Whether to use retrieval-augmented generation (RAG) facilities with the given SQL-GPT contexts when processing this request.

SQL Generation Examples

To generate the SQL equivalent query to a given question using the example.atc_ctx SQL-GPT context:

GENERATE SQL Example

GENERATE SQL FOR
	'What is the callsign and position of the aircraft with most recent timestamp?'
WITH OPTIONS (context_name = 'example.atc_ctx')

To generate the SQL equivalent query to a given question using the nyctaxi_ctx & flights_ctx SQL-GPT contexts with SQL RAG:

GENERATE SQL with RAG Example

GENERATE SQL FOR
	'What was the busiest airport, including taxis and flights, during January and February of 2023?'
WITH OPTIONS (context_names = 'nyctaxi_ctx, flights_ctx', use_rag = 'true')

​Parameters

​SQL Generation Options

​SQL Generation Examples

Parameters

SQL Generation Options

SQL Generation Examples