Project Info

Remi: AI Chef

Inspiration

Remi: AI chef was born out of our passion for cooking and trying new recipes, which for all three of us, has been a way to share our culture and our love with the people we love. We decided to create a tool that lets users customize recipes according to their dietary restrictions, medical conditions, and other preferences, allowing them to enjoy the food they love while making the best choices for their well being.

What it does

Remi harnesses Groq.ai’s powerful AI Inference technology to find ingredient substitutions for recipes submitted by the user. With a series of queries to the LLM models, Remi provides users with alternative ingredients for a wide range of dietary restrictions, as well as medically-informed suggestions for items to omit or include to support patient’s health according to specific conditions, analysis of their protein goals, and scaled quantities according to their requested serving size.

Challenges we ran into

A challenge faced along the way was deciding the appropriate AI models with the many options offered by Groq.ai and other potential tools, however, we conducted an analysis of prompts across the models, which allowed us to select one that not only provides most accurate results, but also presents in a tone that is appropriate for our app.

Accomplishments we're proud of

We are especially proud of our successful integration of Groq.ai's AI tool into our technology, which enabled us to provide medically accurate information about the ingredients in users' recipes. This implementation not only improved the overall user experience by offering health-conscious insights but also demonstrated the practical application of AI in everyday contexts such as nutrition and wellness.

What we learned

During this process, we improved our ability to construct precise and effective prompts for the AI models which was crucial to providing quality information for our users. Integrating Groq.ai into our web application required us to sharpen both our backend and frontend development skills, as we needed to efficiently handle API requests and present our information in an easily digestible format to the end user.

What's next

We hope to continue this project and focus on improving our AI prompts, optimization, and continuing to develop our Ratatouille themed User Interface to create a robust Recipe and Cooking application that allows every user to feel like a chef!

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
FlaskClaimed

5 of 6 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

35 KB

Source files

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

Feature verification

7 Verified1 Code-supported1 Blocked

Dietary restriction based ingredient adjustmentVerified
Remi provides users with alternative ingredients for a wide range of dietary restrictions
Claimed on Devposthigh confidence
- backend/groq_recipe.py:55 — food_restrictions() sends an LLM prompt to adjust ingredients to comply with given food restrictions
- recipe-app/src/components/mainForm.js:12 — UI lets user pick dietary restriction options (Dairy Free, Gluten Free, allergens) and posts them via sendDataToBackend to /api/submit-selections
- backend/groq_recipe.py:213 — /api/submit-selections route calls food_restrictions() with the submitted diet array
Final modified recipe generation and displayVerified
Remi provides users with a personalized cooking assistant workflow producing a tailored recipe (implied by full multi-step process: ingredient swaps, dietary tips, effortless meal prep)
Claimed on Devposthigh confidence
- backend/groq_recipe.py:117 — new_recipe() prompts the LLM to reassemble the original recipe with the modified ingredients into a final formatted recipe
- recipe-app/src/components/finalSubmit.js:11 — FinalSubmitButton fetches /api/submit-recipe and renders the returned final recipe text/list to the user
Medically informed health condition ingredient modificationVerified
medically-informed suggestions for items to omit or include to support patient's health according to specific conditions
Claimed on Devposthigh confidence
- backend/groq_recipe.py:74 — health_modifications() prompts the LLM to modify ingredients based on user-specified health issues while respecting food restrictions
- recipe-app/src/components/mainForm.js:8 — UI presents health condition checkboxes (Diabetes, High Blood Pressure, Kidney Disease, etc.) submitted alongside diet to the backend
- backend/groq_recipe.py:214 — /api/submit-selections calls health_modifications() with submitted health_problems
Protein goal analysis and ingredient adjustmentVerified
analysis of their protein goals
Claimed on Devposthigh confidence
- backend/groq_recipe.py:98 — protein_goals() sends an LLM prompt to adjust ingredient quantities to hit a target protein amount
- recipe-app/src/components/proteinGoals.js:19 — ProteinGoalInput posts the user's protein goal in grams to /api/proteinGoals
- backend/groq_recipe.py:225 — /api/proteinGoals route wires the frontend input to protein_goals()
Recipe ingredient extraction and substitution via Groq LLMVerified
Remi harnesses Groq.ai's powerful AI Inference technology to find ingredient substitutions for recipes submitted by the user
Claimed on Devposthigh confidence
- backend/groq_recipe.py:18 — get_ingredients() calls client.chat.completions.create against Groq's llama3-8b-8192 model to extract ingredients from user recipe text
- backend/groq_recipe.py:148 — /api/process_input Flask route wires the frontend recipe submission to get_ingredients()
- recipe-app/src/components/mainInput.js:19 — MainInput posts the user's recipe text to /api/process_input
Serving size scaling of ingredient quantitiesVerified
scaled quantities according to their requested serving size
Claimed on Devposthigh confidence
- backend/groq_recipe.py:36 — scaling_ingredients() prompts the LLM to multiply ingredient quantities by a scaling factor
- recipe-app/src/components/scaling.js:19 — ScalingInput posts a numeric scale factor to /api/scaling
- backend/groq_recipe.py:172 — /api/scaling route wires the frontend scale factor to scaling_ingredients()
Web application built with Flask backend and React frontendVerified
Built with css, figma, flask, github, groq, html, javascript, python, react.js
Claimed on Devposthigh confidence
- backend/groq_recipe.py:3 — Flask app with flask_cors is the backend server
- recipe-app/src/index.js:1 — React app with react-router-dom implements the frontend routing and pages
Ratatouille themed user interfaceCode-supported
continuing to develop our Ratatouille themed User Interface
Claimed on Devpostlow confidence
- recipe-app/src/components/mainInput.js:44 — Uses a custom 'Sarpanch' font and styled UI elements, but no explicit Ratatouille-branded assets or theming were found beyond generic styling
Demo video / project showcaseBlocked
check out our demo, click this link: https://devpost.com/software/remi-ai-chef
Claimed on readmehigh confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.