Personalized Tour Package Recommendations using AI, Web UI Using Lovable and n8n

Pre requisite:
1. Vetrorize Tours and Activities information in Pinecone Vector Database 
(https://n8n.io/workflows/5085-convert-tour-pdfs-to-vector-database-using-google-drive-langchain-and-openai/)


## UI-Based Query with webhook connecting to Lovable
This flow uses a web UI built using Lovable to query contracts directly from a form interface.

### Webhook Setup for Lovable
Webhook Node
Method: POST
URL: your webhook url
Response: Using 'Respond to Webhook' Node

### Structured Output Parser
Sample structure:
  "itinerary": [
    {
      "dayNumber": 1,
      "date": "2024-07-15",
      "activities": [
        {
          "id": "1",
          "title": "Kuala Lumpur International Airport",
          "description": "Arrival at KLIA",
          "duration": "1 hour",
          "location": "KLIA",
          "type": "transport"
        },



### Lovable UI
User shall submit Destination or Activity Search
Receive response back via the response webhook in a JSON format. 

Data is sent via webhook to n8n and responded with the Package options


⚙️ Tools & Tech Stack
Component	            Tool Used
AI Embedding	            OpenAI text-embedding-3-small
Vector DB	            Pinecone
Chunking	            Recursive Text Splitter
AI Agent	            OpenAI GPT Chat
Structure Output Parser	    Parse Response data in structured JSON format
Automation	            n8n
UI Integration	Lovable (form-based)