Youtube RAG search with frontend using Apify, Qdrant and AI

by Jimleuk ✓ · 4,580 views · created 2025-03-22 · Market Research, AI RAG

What this workflow does

This AI workflow has 49 nodes and runs manually, when you click “Execute workflow” (plus 4 other triggers). Along the way it connects Qdrant Vector Store, Embeddings OpenAI, Redis and OpenAI Chat Model. It also calls api.apify.com and api.openai.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 4 other triggers).

1. Get Latest Youtube Videos (HTTP Request): calls api.apify.com
2. Incr Rate Limit (Redis): incr
3. Generate Webpage (HTML): parses or builds HTML
4. Ignore Already Seen (Remove Duplicates): removes duplicate items
5. Get Video Subtitles (HTTP Request): calls api.apify.com
6. 10req/min (If): checks a condition and branches into true / false
7. Render Page (Respond to Webhook): sends the response back to the webhook caller
8. For Each Video (Loop Over Items (Split in Batches)): loops over the items in batches
9. Chunk Subtitles (Edit Fields (Set)): sets 1 field: vtt
10. Get Query (Edit Fields (Set)): sets or maps fields

…plus 27 more steps. See the full node list below.

Services it uses

Qdrant Vector StoreEmbeddings OpenAIRedisOpenAI Chat Model

HTTP calls to: api.apify.com, api.openai.com

Before you upgrade to n8n 3.0

Nodes used (25)

• Manual Triggern8n-nodes-base.manualTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Edit Fields (Set)n8n-nodes-base.set
• Qdrant Vector Store@n8n/n8n-nodes-langchain.vectorStoreQdrant
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• No Operation, do nothingn8n-nodes-base.noOp
• Waitn8n-nodes-base.wait
• Sortn8n-nodes-base.sort
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Information Extractor@n8n/n8n-nodes-langchain.informationExtractor
• Webhookn8n-nodes-base.webhook
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Ifn8n-nodes-base.if
• Redisn8n-nodes-base.redis
• Execute Sub-workflown8n-nodes-base.executeWorkflow
• Execute Workflow Triggern8n-nodes-base.executeWorkflowTrigger
• Split Outn8n-nodes-base.splitOut
• Schedule Triggern8n-nodes-base.scheduleTrigger
• Remove Duplicatesn8n-nodes-base.removeDuplicates
• HTMLn8n-nodes-base.html
• Markdownn8n-nodes-base.markdown
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi

From the author

Ever wanted to build your own RAG search over Youtube videos? Well, now you can! This n8n template shows how you can build a very capable Youtube search engine powered by Apify, Qdrant and your LLM of choice to quickly and efficiently browse over many videos…

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