Automation library · Content

Scrape and ingest web content into Supabase pgvector

Started by someone opening a chat with it, and works across Supabase and Supabase vectors. It puts OpenAI and OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: OpenAI, OpenRouterRetrieval

18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 5Model 9Logic 2Service 2

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

  1. 1Receive company URLWebhookStarts it
  2. 2Load scraped contentDocument Default Data LoaderModel
  3. 3Generate OpenAI embeddingsEmbeddings Open AiModel
  4. 4Receive chat messageChat triggerStarts it
  5. 5OpenRouter LLMLm Chat Open RouterModel
  6. 6Chat memoryMemory Buffer WindowModel
  7. 7Generate OpenAI embeddings1Embeddings Open AiModel
  8. 8Rerank results with CohereReranker CohereModel
  9. 9Validate and normalize URLCodeLogic
  10. 10Store embeddings in SupabaseVector Store SupabaseModel
  11. 11Answer query from enriched leadsAgentModel
  12. 12Retrieve documents from SupabaseVector Store SupabaseModel
  13. 13Check for duplicate in SupabaseSupabaseService
  14. 14Return URL validation errorRespond To WebhookStarts it
  15. 15Return ingestion resultRespond To WebhookStarts it
  16. 16Skip if already ingestedIfLogic
  17. 17Return duplicate noticeRespond To WebhookStarts it
  18. 18Scrape company website with FirecrawlFirecrawlService

How it's built

Starts on
Someone opening a chat with it
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
Supabase, Supabase vectors
Model
OpenAI, OpenRouter
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 Supabase and Supabase vectors accounts, and a key for OpenAI and OpenRouter. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI and OpenRouter. 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. 18 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 18 steps before you point it at anything that matters.