SQL Generation API

Docs

SQL Generation API

API endpoint for generating SQL queries from natural language

The SQL Generation API allows you to convert natural language queries into SQL statements without executing them. This is useful for applications that need to generate SQL queries programmatically based on user input.

Endpoint

POST /faas/api/sql

Authentication

All requests must include an API key in the Authorization header:

Authorization: Bearer sk_your_api_key

API keys must start with the prefix sk_ and can be generated from your account dashboard.

Request Format

Parameter	Type	Description
`userInput`	string	The natural language query to convert to SQL
`modelId`	string	The ID of the AI model to use for generation (see available models)
`databaseId`	string	The ID of the database to generate SQL for
`chatId`	string	(Optional) The ID of an existing chat to associate with this query

Example Request

{
  "userInput": "Find all users who signed up in the last month",
  "modelId": "gpt-4o",
  "databaseId": "db_12345"
}

Response Format

Field	Type	Description
`chatId`	string	The ID of the chat this query is associated with (new or existing)
`sqlQuery`	string	The generated SQL query
`error`	string \| null	Error message if generation failed
`usage`	object	Token usage information for the request
`userMessageId`	string	ID of the saved user message
`assistantMessageId`	string	ID of the saved assistant message

Example Response

{
  "chatId": "chat_67890",
  "sqlQuery": "SELECT * FROM users WHERE created_at >= DATE_SUB(NOW(), INTERVAL 1 MONTH);",
  "error": null,
  "usage": {
    "promptTokens": 250,
    "completionTokens": 35,
    "totalTokens": 285
  },
  "userMessageId": "msg_12345",
  "assistantMessageId": "msg_67890"
}

Error Codes

Status Code	Description
400	Invalid request format
401	Missing or invalid API key
404	Model or database not found
500	Server error

Limitations

The API has a maximum duration of 60 seconds per request
The generated SQL is not executed against your database
The API only generates the SQL query based on the database schema
All queries and responses are saved to your chat history

Example Usage

const response = await fetch('https://app.chatdb.live/faas/api/sql', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk_your_api_key'
  },
  body: JSON.stringify({
    userInput: 'Show me all customers who made a purchase last week',
    modelId: 'gpt-4',
    databaseId: 'db_12345'
  })
});
 
const data = await response.json();
console.log(data.sqlQuery);

Chat Endpoint Databases Endpoint