POST/api/v1/ai/pages/{slug}/ask

Ask about a page

Answers a question about a page you can read, from its content and the embedded items you can open. Send earlier turns in history to follow up. Streams the answer as server-sent events: delta events, then done.

API token requiredOr edit secret30 per minute per IP

Guide: AI in pages

Code samples and Try it

Path parameters

slugstringRequired
The document's address: the part after markdrop.in/.

Headers

X-Read-Passwordstring
The password of a password-protected document.
X-Edit-Secretstring
The document's edit secret (sk_…), for a document published without an account. See Edit key.
X-Markdrop-Workspacestring
A workspace's id: answer only if the document is in that workspace, else 404. Workspace domains send it; you rarely need it.

Request body

application/json, required

questionstringRequired
Your question. Up to 4,000 characters.
historyarray of any
Earlier questions and answers in this conversation, as {q, a}, oldest first. Up to 40 items.

Responses

200OK.
401No token, or the token is revoked or mistyped.
422The request didn't validate. detail lists each problem, with where it is (loc) and why (msg).
429Too many requests from your IP address. Wait the seconds in Retry-After.

const res = await fetch("https://api.markdrop.in/api/v1/ai/pages/k3x9q2m/ask", { method: "POST", headers: { Authorization: `Bearer ${process.env.MARKDROP_TOKEN}`, "Content-Type": "application/json", }, body: JSON.stringify({ "question": "What's still open?" }), }); const data = await res.text();

import os import requests r = requests.post( "https://api.markdrop.in/api/v1/ai/pages/k3x9q2m/ask", headers={"Authorization": f"Bearer {os.environ['MARKDROP_TOKEN']}"}, json={"question": "What's still open?"}, ) r.raise_for_status() print(r.text)