This week, I pivoted from using LangChain to a machine learning\u2013based approach for the recipe recommendation system. Instead of relying on prompt-based querying, I\u2019m now representing each recipe as a feature vector derived from its ingredients and tags. Similarly, a user\u2019s fridge contents and dietary preferences are converted into a query vector. Recommendations are generated by scoring the similarity between the query and each recipe vector, returning the top 5 most relevant matches.<\/p>\n
In parallel, I made minor UI adjustments to improve the layout and clarity of the Preferences and Recipes tabs, helping prepare the app for future user testing.<\/p>\n
Finish implementing and testing the vector similarity scoring system across a sample recipe dataset.<\/p>\n<\/li>\n
Integrate the recommendation output with the mobile UI.<\/p>\n<\/li>\n
Explore options for caching or pre-processing recipe vectors for performance optimization.<\/p>\n<\/li>\n<\/ul>\n
This new approach gives us more control and flexibility over how recommendations are generated, and sets the stage for fine-tuning the system as we scale.<\/p>\n","protected":false},"excerpt":{"rendered":"
This week, I pivoted from using LangChain to a machine learning\u2013based approach for the recipe recommendation system. Instead of relying on prompt-based querying, I\u2019m now representing each recipe as a feature vector derived from its ingredients and tags. Similarly, a user\u2019s fridge contents and dietary preferences are converted into a query vector. Recommendations are generated … <\/p>\n