An item based recommender system for food recipes based on their ingredients
It is based on the public data available on kaggle: Raw Recipes
The ingredients are first embedded using AI models which are in sentence form. In NLP, sentence embedding refers to a numeric representation of a sentence in the form of a vector of real numbers, which encodes meaningful semantic information
MiniLM: Small and Fast Pre-trained Models for Language Understanding and Generation
More models on this link
- After the ingredients are embedded (in vector form), the cosine similarity is calculated between the user search query and rest of the recipes. Basically finding the angle between two vectors, lesser the angle more similar they are and vice versa
The app is deployed on streamlit server
Medium article: Step by step guide on how to develop this application
Show the nutrition values