Automation library · Customer support

Sync website FAQs to Pinecone weekly with OpenAI

Started by a clock, and works across Pinecone. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 2 loops or waits: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

Download free
19 stepsMedium: a working afternoon
0Branches: places the flow splits
2Loops or waits
1Service it connects to

The flow

Starts it 1Model 3Logic 11Service 4

The steps in the order they run, from what starts it.

  1. 1Schedule Trigger – Every Monday Midnight ISTSchedule triggerStarts it
  2. 2OpenAI Text Embeddings (text-embedding-3-small)Embeddings Open AiModel
  3. 3Load FAQ Chunk TextDocument Default Data LoaderModel
  4. 4Get Sitemap IndexHttp RequestService
  5. 5Upsert FAQ Chunks to PineconeVector Store PineconeModel
  6. 6Parse Sitemap Index XMLXmlLogic
  7. 7Wait 2s Between BatchesWaitLogic
  8. 8Extract Sub-Sitemap URLsCodeLogic
  9. 9Loop URLs in BatchesSplit In BatchesLogic
  10. 10Fetch Sub-SitemapHttp RequestService
  11. 11Scrape Page HTMLHttp RequestService
  12. 12Parse Sub-Sitemap XMLXmlLogic
  13. 13Extract Text, Headings & MetadataCodeLogic
  14. 14Flatten & Filter All URLsCodeLogic
  15. 15Filter: Has Enough ContentFilterLogic
  16. 16Build GPT RequestCodeLogic
  17. 17GPT-4o: Generate FAQsHttp RequestService
  18. 18Parse FAQs & Build ChunksCodeLogic
  19. 19Filter: Valid FAQ Chunks OnlyFilterLogic

How it's built

Starts on
A clock
Steps
19, 2 loops or waits
Size
Medium: a working afternoon
Connects to
Pinecone
Model
OpenAI
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Pinecone account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 19 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 19 steps before you point it at anything that matters.