Wren AI exposes core APIs for answering user questions — including generating SQL from questions, executing queries, explaining results, and producing natural language summaries.

Endpoints Overview

POST /ask: Ask a question and get a direct answer from the AI.
POST /generate_sql: Convert a natural language question into a SQL query.
POST /run_sql: Execute SQL and return structured results.
POST /generate_summary: Generate a natural language summary from .
GET /stream_explanation: Stream natural language explanations for non-SQL questions.

Use these endpoints to build interactive and intelligent data experiences.

When to Use Which API

Wren AI APIs are designed to be modular — you can either call a single all-in-one API or chain multiple endpoints together for more control and flexibility.

🔹 For simple questions

Use this when you just want to ask a question and get an answer:

Scenario	Use This
I want to ask a question and get an answer (AI will generate SQL, run it, and summarize it)	/ask
I want a streamed version with reasoning and progress updates	/stream/ask

🔹 For advanced or modular workflows

Use these if you want more control over each step:

Step	API
Convert question to SQL	/generate_sql, or /stream/generate_sql
Execute the SQL	/run_sql
Summarize the SQL result	/generate_summary
Get explanation when SQL is not applicable	/stream_explanation

💡 Common Combinations

You can mix and match these endpoints based on your product needs.

/generate_sql → /run_sql → /generate_summary

For building interactive BI tools or workflows where SQL needs review, logging, or step-by-step handling.
/ask

Best for chat interfaces or quick answers with minimal effort.
/stream/ask

Best for frontend apps that want to display real-time progress, similar to ChatGPT-style interactions.