Project Info
Inspiration
Poetry can be challenging. Traditionally, it's taught through topics such as love or mortality, and ultimately, might have conditioned us students to think that poetry is boring! However, that couldn't be further from the truth. Thus, we decided to create a website that not only inspires users to write poetry, but also help them improve and hone their skills. Our goal is to spread the joy of writing poetry by making it more accessible and enjoyable for everyone!
What it does
This tool takes a random image from our own curated list of poetry-inspiring catalogue of images, and challenges you to write a poem based off of it. The image is also sent to the Gemini API, which generates its own poem. These poems are both evaluated by Gemini, which outputs a score, and a quick word of advice on how to improve your poem by learning from the AI's example.
How we built it
We integrated the Gemini API to rate and review the poems, limiting its' prompt to a simple JSON file + a bit of advice. The backend was developed using using Node.js. The frontend was designed simply with HTML and CSS.
Challenges we ran into
This was our first time using Node.js, and we had to learn how to manage communication between the frontend and backend. It was also some of our first times coordinating progress among team members to avoid git conflicts and keep our workflow focused.
Accomplishments we're proud of
We're proud of the aesthetically pleasing UI how quickly we learned how to use Node.js. Initially, we had modest expectations, but this hackathon pushed us to our limits and forced us to widen our programming skills.
What we learned
We gained experience in server management, UI development, version control with Git, and effective team communication. Additionally, we improved our understanding of the web design process, full-stack development, Node.js, and CSS animations.
What's next
Future plans include adding difficulty levels, more detailed feedback for each poetry category, and analysis across multiple inputs. We aim to introduce different poem formats (quartets, haikus, sonnets), a timer feature, and both speech-to-text and text-to-speech capabilities.
Analysis
View
Metric
- 68
- 66
- 15
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- Google GeminiIn code
- HTMLIn code
- JavaScriptIn code
- Node.jsClaimed
4 of 5 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
28 KB
Source files
11
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
Hu-Maxwell/PoetRate
48 files · 27.3 MB · @ 9ac4c32
Structure
Interface
6 files · 13%Screens, components and styles rendered to the user.
Application logic
4 files · 8%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- JavaScript56%
- CSS25%
- HTML18%
- Markdown0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
backend/package.json
npm · 4- @google/generative-ai
- dotenv
- fs
- path
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.