Inspiration
We built this project after realizing the amount of work that goes into creating an exam or a quiz. It is very time-consuming, and humans are prone to errors. Hence, this AI tool will help the instructors to create complex question papers.
What it does
Testify accepts 3 PDF files (lecture material) and a prompt that consists of the type of questions that the instructor wants to ask the students. Based on this information, Testify generates the question paper and sends back the response in a pdf.
How we built it
We used OpenAI's Assistant to generate the question. We used Python for the backend to create the server and call the OpenAI's API.
Challenges we ran into
We struggled to get a response from the API initially. We would not connect the front end to the back end. Now, we have a functional back-end server and a website that needs to be implemented.
Accomplishments that we're proud of
This was our first Hackathon, and working with APIs and OpenAI's Assistant was a big win for us. Getting a valid response from the API was amazing. All the questions that have been generated was accurate.
What we learned
Plan before a hackathon.
What's next for Testify
Create a UI for the instructors to use this software.
Built With
- api
- css
- flask
- html
- javascript
- openaiassistant
- python
Log in or sign up for Devpost to join the conversation.