LineaScope

Inspiration

In a world where people’s skills are becoming increasingly specialized and millions of students are seeking ways to delve deep into topics they are interested in, actually processing and gathering relevant information is difficult. By being able to break down and work with existing information quickly, people would be able to gain a much deeper understanding of their interests. That is the vision of LineaScope: making it easy for people across the world to have the ability to educate themselves about topics quickly.

What it does

The prototype I built for LineaScope includes a user management system and the ability to break down website links and PDFs so that users can ask questions about the information they provide. Ultimately, users would be able to input any type of information, ask a question about it, and receive a detailed response back with relevant info.

How we built it

LineaScope uses Vector Databases, enabling the application to retrieve relevant information from a document that can be used to answer a user's questions. Additionally, I used Clerk for a complete user management system, and NextJS with various APIs to parse and send information from the frontend to the backend. In the prototype, this includes website links and PDF files, but I plan on adding other key features such as uploading audio and video files, and being able to interact with multiple sources of information at once.

Challenges we ran into

This hackathon was very instructive. I learned how to use the NextJS framework, Langchain, and Vercel (lots of code bugs and errors all the way from development to deployment, but definitely worth taking the time to fix them).

What's next for LineaScope

User management integration with MongoDB The ability to connect with other students and work on research papers together Optimizing VectorDB input/output Increasing the complexity of what can be inputted into as information

Built With

• clerk
• langchain
• nextjs
• vercel