CultureTrip Planner

A smart travel planner that builds customized trip itineraries based on a user’s tastes (e.g., music, fashion, food, books), mood, or goals (relax, explore, party).

Comment

Inspiration

Our inspiration was to solve a real-life problem, especially issues related to travel. Planning a vacation has always felt overwhelming — scrolling endlessly online for places to go, trying to piece everything together. It’s time-consuming and mentally exhausting.

That frustration sparked this idea. We wanted to create something that makes trip planning easier and more enjoyable. This project comes from a very personal place — it's a problem we genuinely struggle with, and we poured our heart and soul into building a solution.

What it does

The CultureTrip Planner builds personalized trip itineraries based on your mood, tastes (music, food, fashion, books), and travel goals (relaxation, exploration, partying, etc.).

Powered by OpenAI and Qloo’s Taste AI, it crafts immersive experiences tailored just for you.

How we built it

We developed the application using a modern full-stack setup:

  • TypeScript, JavaScript, React, FastAPI, OpenAI, Qloo API, REST API, Tailwind CSS, PostgreSQL

🧠 Workflow Overview

1. User Prompt Input (Frontend)

  • Clean, intuitive input form built in React + Tailwind
  • Users provide: destination, duration, mood/vibe, and tastes (music, movies, food, places)

2. Prompt Parsing & Entity Extraction (Backend – FastAPI)

  • Backend receives input and extracts structured data (genres, preferences, location context)

3. Qloo API Integration

  • Tailored requests to Qloo API return culturally relevant recommendations
  • Results are sanitized for quality, diversity, and relevance

4. OpenAI Prompt Generation

  • Combines user context + Qloo insights to craft prompts for GPT
  • GPT generates creative, emotionally intelligent itineraries

5. Response Delivery & Storage

  • Results displayed in styled daily cards (with Google Maps links, venue details, export options)
  • Each session stored in PostgreSQL for history and reuse

Challenges we ran into

  1. Navigating the Qloo API

    • Understanding endpoints/filters required trial-and-error testing

  2. Python Dependency Management

    • Conflicts between pip and conda had to be resolved

  3. PostgreSQL Deployment & Access Control

    • Initial authentication issues due to misconfigured permissions

  4. OpenAI Rate Limits

    • Hit request limits → optimized frequency and token usage

  5. Video Recording

    • Learned new software for synchronized video/audio demo

Accomplishments we're proud of

  • End-to-End AI-Powered Itinerary Generation
    Personalized travel plan blending Qloo Taste API + OpenAI GPT

  • Smart Prompt Engineering
    Crafted adaptive prompts combining structured insights with natural language

  • Seamless Frontend Experience
    React + Tailwind UI with maps, animations, and styled recommendations

  • Robust Backend Infrastructure
    FastAPI backend integrating APIs, sanitizing data, and persisting sessions

What we learned

  • Prompt Design Matters → balancing creativity + structured data is an art and science
  • API Integration & Sanitization → extracting, cleaning, and feeding third-party data into GPT
  • Geolocation & Personalization → browser geolocation and reverse geocoding for local flavor
  • System Design Thinking → considering UX, backend, rate limits, and persistence holistically

What's next for CultureTrip Planner

  • Budget Mode → show estimated cost/day
  • Taste Timeline → visual chart mapping tastes across days
  • Travel Companion Generator → suggest companions via Qloo profiles
  • Multi-City Planning → seamless multi-city itineraries
  • Offline Mode & PDF Guidebooks → downloadable offline travel guides
  • Real-Time Local Updates → integrate events/weather APIs
  • Airline/Hotel Booking → end-to-end trip management

Built With

Share this project:

Updates