# Dynamic website assistant with DeepSeek: n8n workflow template

> Started by another system calling it, and works across Pinecone. It puts OpenRouter behind a retrieval step, so answers are drawn from documents you supply...

Source: https://millionrounds.com/workflow/dynamic-website-assistant-with-deepseek (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Dynamic website assistant with DeepSeek

Started by another system calling it, and works across Pinecone. It puts OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 28 steps, 1 branch: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenRouter Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fdynamic-website-assistant-with-deepseek)

**28 steps** Large: read it before trusting it with anything live

**1** Branch: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 4 Model 23 Logic 1

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

- 1 **Postgres Chat Memory** Memory Postgres Chat *Model*
- 2 **OpenRouter Chat Model** Lm Chat Open Router *Model*
- 3 **Embeddings Cohere** Embeddings Cohere *Model*
- 4 **Embeddings Cohere6** Embeddings Cohere *Model*
- 5 **Embeddings Cohere7** Embeddings Cohere *Model*
- 6 **Embeddings Cohere9** Embeddings Cohere *Model*
- 7 **Embeddings Cohere10** Embeddings Cohere *Model*
- 8 **Webhook** Webhook *Starts it*
- 9 **Postgres Chat Memory1** Memory Postgres Chat *Model*
- 10 **OpenRouter Chat Model1** Lm Chat Open Router *Model*
- 11 **Embeddings Cohere8** Embeddings Cohere *Model*
- 12 **Postgres Chat Memory2** Memory Postgres Chat *Model*
- 13 **OpenRouter Chat Model2** Lm Chat Open Router *Model*
- 14 **Embeddings Cohere11** Embeddings Cohere *Model*
- 15 **AI Agent for groton** Agent *Model*
- 16 **Pinecone Vector Store5** Vector Store Pinecone *Model*
- 17 **Pinecone Vector Store6** Vector Store Pinecone *Model*
- 18 **Pinecone Vector Store7** Vector Store Pinecone *Model*
- 19 **Pinecone Vector Store9** Vector Store Pinecone *Model*
- 20 **Pinecone Vector Store10** Vector Store Pinecone *Model*
- 21 **Switch** Switch *Logic*
- 22 **AI Agent1 ghostwritingpartner** Agent *Model*
- 23 **Pinecone Vector Store8** Vector Store Pinecone *Model*
- 24 **AI Agent ebook-wr** Agent *Model*
- 25 **Pinecone Vector Store11** Vector Store Pinecone *Model*
- 26 **Respond to Webhook** Respond To Webhook *Starts it*
- 27 **Respond to Webhook1** Respond To Webhook *Starts it*
- 28 **Respond to Webhook2** Respond To Webhook *Starts it*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 28, with 1 branch
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Pinecone
- **Model:** 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 Pinecone account, and a key for OpenRouter. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls 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?

Take your time. At 28 steps it is large: read it before trusting it with anything live.

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 28 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fdynamic-website-assistant-with-deepseek)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Pinecone](https://millionrounds.com/workflows?service=Pinecone#library)

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Build a dual-stage RAG chat assistant with Google Drive** 27 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/build-a-dual-stage-rag-chat-assistant-with-google-drive)
- [**WhatsApp unofficial AI bot with Groq and Pinecone** 26 steps · calls a model · Pinecone, Redis](https://millionrounds.com/workflow/whatsapp-unofficial-ai-bot-with-groq-and-pinecone)
- [**Turn your portfolio into an AI assistant with OpenAI** 25 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/turn-your-portfolio-into-an-ai-assistant-with-openai)
- [**Automated email classification & response system with Groq AI** 34 steps · calls a model · Email, Pinecone](https://millionrounds.com/workflow/automated-email-classification-and-response-system-with-groq)
- [**Build a cost engineering RAG with Google Drive and OpenAI** 22 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/build-a-cost-engineering-rag-with-google-drive-and-openai)
- [**Filter cybersecurity news for your tech stack with OpenAI** 35 steps · calls a model · Gmail, Pinecone](https://millionrounds.com/workflow/filter-cybersecurity-news-for-your-tech-stack-with-openai)