Text to SQL Node

The text to SQL node allows you to generate SQL queries from natural language.

​

Node Inputs

1. Natural language query: The query in natural language
   • Type: Text
2. Schema: The schema you want the SQL query to follow
   • Type: Text

​

Node Parameters

On the face of the node:

1. SQL Database: Choose the SQL database the data is in. The available options are: MySQL, PostgreSQL, Snowflake and SQLite3. The default database is MySQL.

In the gear:

1. LLM model: The llm model you want to use to generate the query. The available options are: o3-mini, o1, o1-mini, o1-preview, chatgpt-4o-latest, gpt-4o, gpt-4o-2024-08-06, gpt-4o-mini, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4 and gpt-3.5-turbo. The default value is gpt-4o.

​

Node Outputs

1. SQL Query: The SQL query generated by the llm
   • Type: Text
   • Example usage: {{nl_to_sql_0.sql_query}}

​

Example

The below example is a pipeline which uses the text to SQL node to generate a SQL query from natural language.

1. Text Node: Stores the natural language query
   • Text: Summarize the data
2. Text to SQL Node: Generates the SQL query
   • SQL Database: MySQL
   • Natural language query: {{input_0.text}}
   • Schema: CREATE TABLE Person ( id INT AUTO_INCREMENT PRIMARY KEY, name VARCHAR(100) NOT NULL, phone_number VARCHAR(20), email VARCHAR(100) UNIQUE, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP );
3. Output Node: Outputs the SQL query
   • Output: {{nl_to_sql_0.sql_query}}

xt to