Project Info
Inspiration
According to NRDC and Harvard Law’s study, around 91% of individuals throw perfectly good food away due to labels like “sell by” and “best by.” In doing so, these individuals contribute to the huge issue of food waste. More importantly, the perfectly good food that gets wasted ends up rotting in landfills, emitting potent greenhouse gases and contributing to the impending climate crisis.
What it does
Our solution is Eatelligent! Eatelligent is an online platform for users to manage their food waste by allowing users to add data about their groceries and they can find recipes that specifically prioritize ingredients which are going to expire soon.
How we built it
Frontend: Typescript, Javascript, CSS Database: MongoDB Atlas to store data about user preferences, ingredients, and recipes Tech Stack: MERN Authentication: Firebase Authentication LLM: Python, HuggingFace API, Llama-3.1-8B-Instruct to generate user-specific recipes
Challenges we ran into
Initially, we had planned for our project to be a mobile application. However, due to issues of not being able to convert our MERN stack web application into a mobile application and time constraints, we had to resort to making a web application rather than a mobile application. Another challenge we faced was trying to get the LLM portion of the project to connect to the rest of web application. Despite a lot of trial and error, we were not able to fix the issue. However, something we would like to do in the future is create a seamless connection between the LLM and the web application to show the full impact of our idea.
Accomplishments we're proud of
We are proud of ourselves for participating and pushing out a product that has features that work well and convey our vision despite facing a lot of problems in implementation.
What we learned
As it was most of our members' first time implementing the MERN stack, we are happy that we gained valuable experience learning how this specific tech stack works and can be implemented. Additionally, we learned how to manage and connect the stack with authentication by implementing Firebase authentication to handle secure user sign-up, login, and session management.
What's next
Some things we hope to implement in the future for Eatelligent is: Fixing the LLM implementation and integration with our current web application Converting the application into mobile application -Add a system that allows the user to take images of their groceries to extract information rather than manually adding information for their groceries Implementation push notifications Deploy with Vercel
Eatelligent
Project Descrption:
According to studies by the NRDC and Harvard Law, approximately 91% of individuals discard perfectly good food due to confusing labels like “sell by” and “best by.” This contributes significantly to food waste, which eventually rots in landfills and emits potent greenhouse gases. Eatelligent is an online platform designed to combat the climate crisis by helping users manage food waste. Users can track their groceries and generates custom recipes that specifically prioritize those soon-to-expire ingredients.
Tracks
- Sustainability
- Best SlugHacks
- Use of GenAI
- Most Start-up Potential
- Best Use of MongoDB
Tech Stack:
Frontend: TypeScript, JavaScript, CSS (React/Vite)
Database: MongoDB Atlas to store user preferences, ingredients, and recipe data.
Authentication: Firebase Authentication for secure sign-up, login, and session management.
LLM: Python, HuggingFace (Llama-3.1-8B-Instruct) to generate dynamic, user-specific recipes based on inventory.
Challenges & Learnings:
We originally envisioned Eatelligent as a mobile application. However, due to the complexities of converting a MERN stack web app into a mobile environment within the hackathon time constraints, we pivoted to a high-quality web application.
What We Learned:
As first-time users of the MERN stack, we gained deep experience in connecting a full-stack architecture with external services. We successfully integrated Firebase for security and LLMs for intelligent response generation, learning how to manage data flow between the database and the AI.
What’s Next for Eatelligent:
-
Mobile Conversion: Porting the web experience to a native mobile app.
-
Computer Vision: Implementing an image-recognition system so users can photograph groceries to auto-extract data instead of manual entry.
-
Deployment: Launching a live version via Vercel.
Steps to Run the Application:
- Start the Server Navigate to the server directory in your terminal: python recipe_generation.py
- Run these two commands: cd server npm install node --env-file=.env server
- Start the Client Open a new terminal window and navigate to the client directory: cd client npm run dev
- Access the App Click the local link provided in your terminal (e.g., http://localhost:5173) to view the live project.
Analysis
View
Metric
- 16
- 10
- 9
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
- ExpressIn code
- FastAPIIn code
- HTMLIn code
- Hugging FaceIn code
- JavaScriptIn code
- MongoDBIn code
- PythonIn code
- PyTorchIn code
- ReactIn code
- Tailwind CSSIn code
- TypeScriptIn code
- FirebaseClaimed
12 of 13 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
131 KB
Source files
63
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
Pinkspring01/Eatelligent
103 files · 1.8 MB · @ dfd0c7d
Structure
Interface
32 files · 31%Screens, components and styles rendered to the user.
API & routing
13 files · 13%Request entry points: routes, handlers and controllers.
Application logic
17 files · 17%Domain rules, services and shared utilities.
Data & schema
2 files · 2%Schema definitions, migrations and data access.
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
- JavaScript52%
- TypeScript21%
- CSS13%
- HTML5%
- Markdown5%
- Python4%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
EatelligentMobile/package.json
npm · 30- @expo/vector-icons
- @react-navigation/bottom-tabs
- @react-navigation/elements
- @react-navigation/native
- expo
- expo-constants
- expo-font
- expo-haptics
- expo-image
- expo-linking
- expo-router
- expo-splash-screen
- expo-status-bar
- expo-symbols
- expo-system-ui
- expo-web-browser
- react
- react-dom
- +12 more
requirements.txt
pypi · 25- accelerate
- faiss-cpu
- fastapi
- ftfy
- google-cloud-firestore
- huggingface-hub
- loguru
- numpy
- opencv-python
- pandas
- pillow
- psycopg2-binary
- pytesseract
- python-dotenv
- regex
- requests
- scikit-learn
- sentencepiece
- +7 more
client/package.json
npm · 21- expo
- react
- react-dom
- react-native-safe-area-context
- +17 more
server/package.json
npm · 8- cors
- dotenv
- express
- express-session
- mongodb
- mongoose
- passport
- passport-google-oauth20
functions/package.json
npm · 3- firebase-admin
- firebase-functions
- +1 more
package.json
npm · 2- cors
- mongodb
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.