Dynamic website assistant with DeepSeek AI, Pinecone Vectorstore & site-based routing

by moosa ✓ · 866 views · created 2025-07-23 · Support Chatbot, AI RAG

What this workflow does

This AI workflow has 28 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects Postgres Chat Memory, OpenRouter Chat Model, Pinecone Vector Store and Embeddings Cohere.

How it runs

Trigger: When an HTTP GET request hits its webhook URL.

1. Switch: routes items into 3 branches
2. AI Agent: runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Pinecone Vector Store); memory: Postgres Chat Memory
3. AI Agent: runs an AI agent, with model: OpenRouter Chat Model; 1 tool (Pinecone Vector Store); memory: Postgres Chat Memory
4. AI Agent: runs an AI agent, with model: OpenRouter Chat Model; 5 tools (Pinecone Vector Store, Pinecone Vector Store, Pinecone Vector Store, Pinecone Vector Store…); memory: Postgres Chat Memory
5. Respond to Webhook: sends the response back to the webhook caller
6. Respond to Webhook: sends the response back to the webhook caller
7. Respond to Webhook: sends the response back to the webhook caller

Services it uses

Postgres Chat MemoryOpenRouter Chat ModelPinecone Vector StoreEmbeddings Cohere

Before you upgrade to n8n 3.0

Nodes used (8)

• Postgres Chat Memory@n8n/n8n-nodes-langchain.memoryPostgresChat
• OpenRouter Chat Model@n8n/n8n-nodes-langchain.lmChatOpenRouter
• Pinecone Vector Store@n8n/n8n-nodes-langchain.vectorStorePinecone
• Embeddings Cohere@n8n/n8n-nodes-langchain.embeddingsCohere
• Webhookn8n-nodes-base.webhook
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Switchn8n-nodes-base.switch
• AI Agent@n8n/n8n-nodes-langchain.agent

From the author

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. 🚀 Overview This workflow enables a powerful AI-driven virtual assistant that dynamically responds to website queries using webhook input, Pinecone vector…

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