New Redis vector store node to reduce LLM cost and increase semantic search!

Ever wonder how you could save on LLM token usage when people ask the same or SEMANTICALLY similar questions?

Enter the new Redis Vector store node!

This is from a template workflow on n8n’s website:

“Stop Paying for the Same Answer Twice

Your LLM is answering the same questions over and over. "What's the weather?" "How's the weather today?" "Tell me about the weather." Same answer, three API calls, triple the cost. This workflow fixes that.

What Does It Do?

Semantic caching with superpowers. When someone asks a question, it checks if you've answered something similar before. Not exact matches—semantic similarity. If it finds a match, boom, instant cached response. No LLM call, no cost, no waiting.

First time: "What's your refund policy?" → Calls LLM, caches answer

Next time: "How do refunds work?" → Instant cached response (it knows these are the same!)

Result: Faster responses + way lower API bills”

This is HUGE! Cutting the cost of api usage AND speeding up responses!

Here is a downloadable template to play with for now. I’ll be releasing a video this next week showcasing how to setup and use it!

https://n8n.io/workflows/10887-reduce-llm-costs-with-semantic-caching-using-redis-vector-store-and-huggingface/

6 comments