SQL to SQL Generators

Integrate the SQL-to-SQL generators in your application.

Please read the getting started guide first.

Example
Endpoint
Options
Response
Questions

Example

You can integrate with our platform by using a simple fetch request:

            
              
            
            const response = await fetch('https://api.sqlai.ai/api/public/v1', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    authentication: `Bearer ${SECRET_TOKEN}`,
  },
  body: JSON.stringify({
    prompt: 'SELECT * from users;',
    mode: 'optimizeSQL',
    engine: 'postgres',
  }),
});
const { query, error } = await res.json();

if (error) {
  // Handle error
}

// Run generated SQL query on your database
const data = await client.query(query);

Endpoint

Send POST request to:

            
              
            
            https://api.sqlai.ai/api/public/v1

Options

Options when requesting a SQL generation:

prompt (required): The SQL query.
mode (required): "optimizeSQL", "fixSQL", "simplifySQL", "formatSQL", "databaseIndex".
engine: The database engine to use:
- mysql
- postgres
- oracle
- mssql
- snowflake
- mariadb
- sqlite
- bigquery
- mongodb
- sql (native SQL is default)
engineVersion: Database engine version number/code as string, e.g. "16", "5.7", "21c".
dataSourceId: Use a data source when generating SQL, e.g. database schema hosted on SQLAI.ai.
dataSourceRaw: Use included data source to generate SQL. CSV format recommended for SQL databases with: table_name, table_column, table_type (table type can be left out if needed, AI can usually infer it).

Response

The above example will return this response:

            
              
            
            {
  "query": "SELECT actor_id, first_name, last_name, last_update\nFROM actor\nWHERE actor_id = 13;",
  "content": "```sql-answer\nSELECT actor_id, first_name, last_name, last_update\nFROM actor\nWHERE actor_id = 13;\n```",
  "queries": {
    "markdown": ["```sql\nSELECT actor_id, first_name, last_name, last_update\nFROM actor\nWHERE actor_id = 13;\n```"],
    "clean": ["SELECT actor_id, first_name, last_name, last_update\nFROM actor\nWHERE actor_id = 13;"]
  },
  "meta": { "usage": { "prompt_tokens": 598, "completion_tokens": 28, "total_tokens": 626 }, "finish_reason": "stop" }
}

The response object type:

            
              
            
            type ResponseBody = {
  query: string; // Generated SQL query stripped of formatting
  content: string; // Complete Markdown generation
  queries: {
    markdown: string[]; // All SQL queries with formatting
    clean: string[]; // All SQL queries stripped of formatting
  };
  meta: {
    usage: { completion_tokens: number; prompt_tokens: number; total_tokens: number };
    finish_reason: 'stop' | 'length' | 'tool_calls' | 'content_filter' | 'function_call';
  };
  error: string | undefined;
};

Questions