Project Info

HalalScan

This project did not submit a demo video on Devpost.

Inspiration

As a muslim, the inspiration for HalalScan came from the challenges that many Muslims (including myself) face in finding halal food options. As a team, we wanted to create a tool that makes it easier for people to identify halal and non-halal ingredients in food products quickly and accurately.

What it does

HalalScan is a website that lets users to input ingredient lists, and identifies whether the ingredients are Halal or Haram thanks to OpenAI's technology. It simplifies the decision-making process for individuals and manufacturers by providing clear results. The user takes a photo, copies the text from the image (a feature often seen in both Apple and Android phones), pastes it in the textbox, presses on the submit button, and awaits for their result (either HALAL, meaning islamically permissible, or HARAM, meaning islamically impermissible).

How we built it

HalalScan was built using HTML, CSS, JavaScript, OpenAI's API, and a lot of help from ChatGPT. We used the following prompt: `If the following ingredient list includes the words alcohol, pork, ham, bacon, gelatin, output the word HARAM alone and if it doesnt include those words output the word HALAL alone: '${ingredientText}'

Challenges we ran into

Our initial attempt in building HalalScan involved exploring technologies like MindsDB and Reflex, but due to time constraints and slow internet connectivity, we decided to focus on a more simple and straightforward web-based solution.

Accomplishments we're proud of

We actually finished building it on time We built something functional!! We built something people truly want Learning more about APIs in general

What we learned

Adaptability is key. Sometimes the simplest method (i.e not using every sponsor's technology) is what leads to success.

What's next

We hope to rely less on OpenAI and build a model of our own. We could also explore potential collaborations and partnerships to make HalalScan readily available to a wider audience.

Analysis

Compare with all teams

View

Metric

latifahalabbad
1

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

Found in codeClaimed only

CSSIn code
HTMLIn code
JavaScriptClaimed

2 of 3 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

4.6 KB

Source files

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.