HackStack

Project Info

title in progress

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Our inspiration came from the idea of family bonding through cooking and the educational potential of interactive learning experiences. We noticed that parents often struggle to involve their children in the kitchen due to the complexity of recipes. We wanted to create a bridge that not only simplifies cooking instructions for children but also turns the cooking experience into an enjoyable and educational activity, fostering a love for cooking and self-reliance from a young age.

What it does

Our web application transforms sophisticated recipes into child-friendly formats. When a parent inputs a recipe, our system uses GPT to distill the instructions into simpler steps. Each step is paired with an image generated by DALL-E to visually guide the child through the cooking process. Additionally, we've integrated Wispr.ai's voice recognition, allowing kids to interactively ask questions about the recipe, just like they would with a parent or a cooking instructor.

How we built it

We developed a web-based platform with separate views for adults and children. The adult view allows parents to upload recipes and assign them to their kids. We utilized React.js for the frontend, building a responsive and intuitive interface. For the backend, we chose Flask due to its simplicity and efficiency in handling RESTful APIs. GPT simplifies the text, DALL-E creates the images, and Wispr.ai powers the voice interaction. We seamlessly integrated these AI technologies to work cohesively, providing an end-to-end solution from recipe upload to interactive cooking guidance.

Challenges we ran into

Cors and parent child communication. We were working with essentially two different states at once, and having them interact with each other while also reducing async issues was a challenge.

Accomplishments we're proud of

Setting up the backend and the integration. For 36 hours this was an extremely thorough backend and frontend with a lot of moving parts. Understanding how to work synchronously and together was very important.

What we learned

Test driven development would have aided a lot of issues in the process. Once we were at the final stages of development, we ran into issues on integrating different parts of the backend together. Additionally, we saw the power of planning using UML diagrams. Seeing the interactions between the different servers was a good visualization for us to continue the development.

What's next

Definitely integrating more features and recipes and trying to scale it from a server perspective. Right now the calls are a bit slow, so optimizing that through parallel processing is important for the app to seam very seamless.

Analysis

Compare with all teams

View

Metric

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
  • FlaskIn code
  • HTMLIn code
  • JavaScriptIn code
  • OpenAIIn code
  • PythonIn code
  • ReactIn code

7 of 7 appear in the indexed code.

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

54 KB

Source files

35

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

0 stars