Find TikTok video questions from keywords using Dumpling AI + GPT-4

by Yang ✓ · 329 views · created 2025-10-03 · Market Research, AI Summarization

What this workflow does

This AI workflow has 14 nodes and runs when someone submits an n8n form (“Tik Tok Search ”). Along the way it connects OpenAI. It also calls app.dumplingai.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Tik Tok Search ”).

1. Search TikTok Users (Dumpling AI) (HTTP Request): calls app.dumplingai.com (POST)
2. Split Search Results into Users (Split Out): splits a list into separate items
3. Limit: keeps the first few items
4. Loop Through TikTok Users (Loop Over Items (Split in Batches)): loops over the items in batches
5. Split Videos from Profile (Split Out): splits a list into separate items
6. Wait: waits 15 seconds
7. Loop Through Videos (Loop Over Items (Split in Batches)): loops over the items in batches
8. Get TikTok Profile Videos (Dumpling AI) (HTTP Request): calls app.dumplingai.com (POST)
9. Get Comments for Each Video (HTTP Request): calls app.dumplingai.com (POST)
10. Extract Clean Comments (Python) (Code): runs custom Python code

…plus 2 more steps. See the full node list below.

Services it uses

OpenAI

HTTP calls to: app.dumplingai.com

Before you upgrade to n8n 3.0

Nodes used (10)

• No Operation, do nothingn8n-nodes-base.noOp
• n8n Form Triggern8n-nodes-base.formTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Split Outn8n-nodes-base.splitOut
• Limitn8n-nodes-base.limit
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Waitn8n-nodes-base.wait
• Coden8n-nodes-base.code
• OpenAI@n8n/n8n-nodes-langchain.openAi
• Data tablen8n-nodes-base.dataTable

From the author

Who’s it for This template is perfect for content creators, social media strategists, and marketing teams who want to uncover trending questions directly from real TikTok audiences. If you spend hours scrolling through videos to find content ideas or audience…

View the original on n8n.io → Check your own copy