Get AI-generated follow-up question suggestions to help users continue their exploration.
Bearer token obtained from the authenticate endpoint.
ID of an existing chat to generate follow-ups for. The conversation history will be used as context.
Alternative to chat_id. Provide an array of user message strings directly.
You must provide either chat_id or user_messages, but not both.
This endpoint is rate-limited to 10 requests per minute with a 5-request burst over 10 seconds, both per JWT. Excess requests return 429 with a Retry-After header.
Response
List of suggested follow-up questions.
curl -X POST https://api.trellis.sh/v1/chats/followups \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"chat_id": "chat_abc123"}'
import requests
response = requests.post(
"https://api.trellis.sh/v1/chats/followups",
headers={
"Authorization": "Bearer YOUR_TOKEN",
"Content-Type": "application/json"
},
json={"chat_id": "chat_abc123"}
)
followups = response.json()["followups"]
const response = await fetch("https://api.trellis.sh/v1/chats/followups", {
method: "POST",
headers: {
Authorization: "Bearer YOUR_TOKEN",
"Content-Type": "application/json",
},
body: JSON.stringify({ chat_id: "chat_abc123" }),
});
const { followups } = await response.json();
{
"followups": [
"How does this compare to the same period last year?",
"Which product category had the highest growth?",
"Can you break this down by region?"
]
}
{
"detail": "Rate limit exceeded",
"retry_after_seconds": 6
}