Handle guest inquiries for multiple rentals with Pinecone Assistant and GPT-4.1

Go to Workflow
77 views
Built by Pinecone Pinecone
Created on June 13, 2026

Description

Vacation rental property manager with multiple Assistants

🛠️ Read about how multi-domain RAG works and other use cases by working through this tutorial on the n8n Blog here.

This workflow shows you how a vacation rental property manager can manage multiple properties each with different information using Pinecone Assistant. Guests can ask questions about their property and get a personalized answer back.
What is Pinecone Assistant?

Pinecone Assistant allows you to build production-grade chat and agent-based applications quickly. It abstracts the complexities of implementing retrieval-augmented (RAG) systems by managing the chunking, embedding, storage, query planning, vector search, model orchestration, reranking for you.

Try it out

Prerequisites

A Pinecone account
A GCP project with Google Drive API enabled and configured
An Open AI account and API key

Setup

Create three Pinecone Assistants in the Pinecone Console here
Name your Assistants n8n-vacation-rental-property-lakeside, n8n-vacation-rental-property-birchwood, n8n-vacation-rental-property-hillcrest
Use the Connect to Pinecone button to authenticate to Pinecone or if you self-host n8n, create a Pinecone credential and add your Pinecone API key directly
Setup your Google Drive OAuth2 API and OpenAI credentials in n8n
Select your Assistant Name in each of the respective Pinecone Assistant nodes
Ask Claude or ChatGPT to generate fictional data in markdown file(s) for each property. You'll use this data in the next step. Using this prompt:
Generate fictional data in markdown format in multiple files for three fictional vacation rental properties in a fictional city. The rental property names are:
Hillcrest Haven** – cozy hillside cottage
Birchwood Retreat** – wooded cabin
Lakeside Loft** – modern loft near the water

Include house manual and rules, wifi codes, local restaurant, coffee shop, outdoor recreation, and entertainment recommendations, and fictional appliance manuals for the air fryer, coffee pot, tv, and washer and dryer.

All addresses, cities, names, phone numbers should be fictional. Each set of files should be named based on their property name like "hillcrest_haven_house_manual.md".
Note: If you don't want to generate your own files, you can use these files.

Add the files to three separate Drive folders named lakeside, birchwood, and hillcrest
Activate the workflow to upload the documents to Pinecone
Once the data is uploaded, ask questions in the chat about a property:
I need help with the coffee maker
The air fryer isn't working at the Lakeside property

Ideas for customizing this workflow

This workflow uses one Assistant per property. You could also use one Assistant and separate the data by setting a metadata field, property, to the name of the property the file is for.
Use your own data and customize to your use case with multiple store locations, restaurants, teams, etc.

Need help?

You can find help by asking in the Pinecone Discord community or filing an issue on this repo.

Nodes Used (4)

AI Agent
@n8n/n8n-nodes-langchain.agent
Google Drive
n8n-nodes-base.googleDrive
OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow