CodeBook

Go-to platform for Computer Science students, Software Developers, and basically anyone who codes.

Comment

Inspiration

The track that we’ve chosen to build a project in is Education. We used this opportunity and our skills to tackle the various issues faced by Computer Science students, Software engineers, and basically anyone who codes. In our own careers as software engineers, there have been many situations when we've needed to repeatedly find up how to code something in a certain language. The upkeep of a collection of frequently-used snippets for a specific language/framework would have been beneficial. An app, where we can get code snippets by just giving a one-line prompt, which can explain what our code is doing exactly, and can also provide us an option to translate codes from one programming language to another. As a result, we developed CodeBook to enable users to store and exchange code snippets as well as translate, explain, and generate codes with ease. We created it to be the go-to platform for students studying computer science, software developers, and pretty much everyone else who codes.

What it does

  • The webapp allows users to share and discuss snippets of code spanning across many languages and frameworks.
  • It has an Auto Code feature where you can give a one-line prompt, and it will give you a precise code based on your prompt.
  • Many a time we come across a piece of code or a function that we are unable to understand. Here comes our Explain Code feature, which when given the code as input, gives an accurate and detailed explanation of what that code is doing.
  • Oftentimes we find solutions to a coding problem in a programming language that we don't understand, in that case, how amazing it'd be if we could easily convert the code to another language in which we are comfortable. We have the Translate Code feature just for that: Input in one language and the model will convert it into the desired language.
  • We have also added an AI assistant that basically answers anything you ask. While coding or let's say doing our assignments we come across a lot of terms and concepts that we don't know/understand, this chatbot will be our savior for those times.

How we built it

We built this app using HTML, CSS, and Javascript for the frontend and used Django in the backend and SQLite as the database. We leveraged Open AI's gpt-3 natural language model and fine-tuned it iteratively to develop the various features of our application. We also integrated CodeMirror's code editor into our website for a seamless and prettified user experience.

Challenges we ran into

  • Priming the gpt-3 model was the trickiest part for us as we had to prime it multiple times for developing the various features for different use cases while not compromising on the results.
  • Also, integrating the gpt-3 model into our web app was daunting, as the model worked fine separately but ran into errors and didn't fetch results when integrated in the pipeline.

Accomplishments that we're proud of

Proud to have completed a fully-fledged application in a relatively short duration of time.

What we learned

We learned some new soft skills in time management, and also some technical skills in databases, backend development, and a lot about GPT-3.

What's next for CodeBook

Some features that we had to leave out of CodeBook include: searching, viewing user profiles, uploading profile images, and other multimedia so it could become like a social media app for Computer Science folks. Also, we wanted to add a discussion forum where people could ask questions. Ideally, we would expand on these features and flesh out the app more.

Built With

Share this project:

Updates