FastGPT icon

FastGPT

AI智能客服平台

对话 → 猜你想问

AI-generated

Summary

Generates suggested follow-up questions ("猜你想问") for an existing FastGPT conversation by POSTing to /core/ai/agent/v2/createQuestionGuide. The model and prompt can be overridden, or the app's latest published config is used.

Inputs

  • 应用ID (required) — FastGPT App ID. Sent as body field appId.
  • 对话ID (required) — chatId of the conversation to generate suggestions for. Sent as body field chatId.
  • 引导配置 — Optional single config block (配置项) with 启用 (open, default true), 模型 (model, blank = app default model) and 自定义提示词 (customPrompt, has a default Chinese prompt). If added, it is sent as the questionGuide body object. If omitted, FastGPT uses the app's latest published configuration.
  • Request Options — Standard n8n request settings: batching (items per batch, interval), ignore SSL issues, proxy, and timeout (default 10000 ms).

Output shape

The parsed JSON response from the FastGPT endpoint, which is expected to contain the generated suggested questions. The source does not define the exact response schema.

Errors throw a NodeApiError if the HTTP status is 4xx/5xx or the response body's code is not 200. The error message is taken from the body's message field. The node sets ignoreHttpStatusErrors so these are handled by this check. Authentication uses the fastGPTApi credential and its baseUrl.

Examples

Example 1: Show follow-up question buttons after a chatbot reply

Set 应用ID and 对话ID (the chatId used in the chat call). Leave 引导配置 empty to use the app's published settings.

Example 2: Generate suggestions with a specific model and prompt

Add 引导配置, set 模型 to e.g. GPT-4o-mini and write a custom 自定义提示词, keeping 启用 true.

Links

Discussion