HackStack

Project Info

Food finder

Devpost

This project did not submit a demo video on Devpost.

##

Inspiration

The inspiration for our restaurant recommender app came from a desire to make dining out a more personalized and enjoyable experience. We wanted to create a tool that would take user preferences and references into account, providing highly tailored restaurant recommendations. By integrating the Yelp API for business data and the OpenAI API for generating responses, we aimed to deliver a unique and interactive way for users to discover great places to eat.

What it does

Our app is a chat bot that provides intelligent restaurant recommendations based on the user's preferences and location.

How we built it

Our tech stack is fastAPI back end and react front end. We used Yelp API to get restaurants near the users current location, retrieved from the user's IP. We then constructed a prompt for OpenAI using relevant information from the Yelp API response. This provides the chat bot with context for the conversation, allowing it to have knowledge nearby food options. For example, the user can ask for "vegan" and the bot is intelligent enough to recommend something like "Indian".

Challenges we ran into

One of the challenges we faced was getting the app running and getting the frontend and backend to communicate with one another. We were using flask at first and post requests were being redirected to get requests. We thought it was the network or something wrong with the frontend but once we refactored to fastAPI that resolved the issues we were facing.

Accomplishments we're proud of

We are able to make the connection between the frontend and backend, and the chatbot is able to provide the user with intelligent restaurant recommendations near the user's location.

What we learned

We learn to work with web frameworks and tools like Flask, FastAPI, OpenAI, React/TypeSrcipt, YelpAPI and we got good practice with teamwork and problem solving.

What's next

We want to use MapsAPI to calculate the distance between each restaurant and the user. So the user can ask for recommendations within a certain distance.

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
  • HTMLIn code
  • JavaScriptIn code
  • PythonIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • FastAPIClaimed

7 of 8 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

15 KB

Source files

23

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

0 stars