Skip to main content

Quick Start

This guide will help you make your first API call to Wren AI. We'll walk through a simple example of generating a SQL query from a natural language question.

Prerequisites​

Basic Example​

Here's a simple example of generating a SQL query using curl:

curl -X POST 'https://cloud.getwren.ai/api/v1/generate_sql' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "projectId": 1,
    "question": "Show me all customers"
  }'

Response:

{
  "id": "1fbc0d64-1c58-45b2-a990-9183bbbcf913",
  "sql": "SELECT * FROM \"olist_customers_dataset\"",
  "threadId": "9c537507-9cec-46ed-b877-07bfa6322bed"
}

Follow-up Questions​

You can maintain conversation context using the threadId from the previous response:

curl -X POST 'https://cloud.getwren.ai/api/v1/generate_sql' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "projectId": 1,
    "question": "list top 10 only",
    "threadId": "9c537507-9cec-46ed-b877-07bfa6322bed"
  }'

Handling Questions that can't be translated to SQL​

If a user asks a question that isn't related to your data schema or can't be translated to SQL, you'll receive an error response:

curl -X POST 'https://cloud.getwren.ai/api/v1/generate_sql' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "projectId": 1,
    "question": "What can you do?"
  }'

Response:

{
  "id": "75c13d09-6f86-4e79-a00e-a4f85f73f2d7",
  "code": "NON_SQL_QUERY",
  "error": "User asks about Wren AI's features and capabilities, unrelated to database schema.",
  "explanationQueryId": "71b016c5-42bb-4897-82d6-46f9b0bf7d94"
}

You have two options to handle this:

  1. Use the error message to generate your own response to users
  2. Stream Wren AI's explanation to users using the stream_explanation endpoint. Check out the API Reference for more details.

Next Steps​

For complete API documentation, visit our API Reference.