Inspiration: Making friends as an adult can be really challenging. And finding a group where you genuinely feel like you belong? That’s even harder. That’s what inspired us to create Connectify — a space designed to make it easier to build real, lasting connections. The idea also came from the experience of being part of this event and forming such a fantastic team. It reminded us just how powerful it is to find the right people and work together toward something meaningful.

What it does : Connectify matches users with people or friend groups who share similar hobbies, values, and personal traits. After answering a series of questions, users are shown their top three most compatible matches, making building meaningful and lasting connections easier.

How we built it : Our website is built using Python. We started by developing a questionnaire for users and then created a local database to store their responses. Next, we implemented Sentence Transformers embedding to convert the users' data into high-dimensional vectors. We also utilized the Qdrant vector database to store these vectors and identify potential friends by calculating the cosine similarity between user vectors.

Challenges we ran into : Understanding how to turn text into vector data and store that in a vector database.

Accomplishments that we're proud of: We're proud to have finished the project and to see our idea successfully implemented.

What we learned : We learned about grouping vectors and semantic similarity using the cosine function.

What's next for Connectify:

In future versions, users will be able to: • Select suggested users from their top matches to form a group • Share social handles, emails, or numbers (optional) for easier communication • Recommend others to join groups or request to join one We’re building toward a smarter, more inclusive friendship experience — one that values who you are and helps you find your people.

Built With

Share this project:

Updates