ChefExtract - Extract recipes from YouTube & cooking sites

Extract cooking recipes from YouTube videos, Shorts, websites, and photos. Make them vegan and order the ingredients on your favourite delivery app with one tap.

Comment

Inspiration

I love cooking, and I like trying recipes I find on YouTube, Instagram, and cooking websites. If I like a recipe, I save it on YouTube, IG, in my Notes app, or bookmark it.

However, since I cannot save them in a single place, it is hard to find them later or categorize them. The worst part? Every time I reopen a recipe, I need to watch ads, accept cookies, reject newsletters, and close useless chatbots. Often, websites are not optimized for mobile either.

After watching Eitan's video, it just clicked! ChefExtract saves my recipe in the app and allows me to add ingredients to my preferred food delivery app.

What it does

ChefExtract does three things:

  1. converts a URL or a picture into a recipe and saves it in a cookbook on my device,
  2. creates a vegan variation based on a recipe I saved,
  3. allows me to add ingredients to my favorite delivery app.

How we built it

First of all, I started from a personal problem, which became the core functionality of the app: saving a recipe I found online on my phone.

I built the whole project on React Native to ensure cross-platform compatibility I am using the YouTube API for URLs that point to YouTube. Otherwise, the Gemini API takes care of it.

The mobile app and the services it uses are hosted on Google Cloud Platform (GCP) to keep everything in the same ecosystem: APIs, hosting, Cloud functions to handle API services, and avoid exposing keys.

Challenges we ran into

Unfortunately, it seems food delivery platforms don't allow adding ingredients to users' "shopping carts" through API. So we cannot do that automatically for users. However, I found a workaround so that when users click on an ingredient, they land on that ingredient's page on their preferred delivery platform.

Accomplishments that we're proud of

I am very proud of the time I spend on GCP in general (instead of using Firebase that I know better but is less used in enterprises). I have a better understanding of the services, the logic, etc. This will be very useful in every future project.

I am also proud of the workaround I found to get users to land on the ingredient's page of their preferred food delivery app.

What we learned

I learned more about GCP: Google Cloud Functions, the logic of setting up projects and assigning them to a billing org. Using different Gemini models based on the needs and ROI. For example, we allow creating a small thumbnail image for recipes. The image is small and provides limited value. Using gemini-2.5-flash-image is enough, instead of gemini-3. I got to know more about RevenueCat and their APIs. I still have a basic knowledge, but this is a useful tool for other projects.

What's next for ChefExtract

  1. Create recipes from ingredients I have in the fridge (and possibly find open-source online recipes). I have a proof of concept with an api recipes online. Not sure I'll be able to include it in the submission.
  2. Improve extraction from other sources like Instagram and TikTok
  3. Swap ingredients to take into account food restrictions or diets (low-carbs, keto, high protein, etc.)
  4. Add categories
  5. Polish some UX/UI patterns
  6. Finalize Android app and web version
  7. Allow users to adjust doses for more or fewer people
  8. Make it more interactive, e.g. users could get a random recipe from a database, or we could propose weekly new recipes based on the saved recipes.

Built With

Share this project:

Updates