It was Friday evening and I needed to make myself lunch after work. I found myself staring into my fridge wondering what to cook. I had leftovers from last night, however, I needed to make something fresh and exciting. I thought to myself, why not go with Dan’s idea and build a personal AI kitchen assistant to analyze the ingredients you have and suggests delicious dishes tailored precisely to your pantry?
This is where Large Language Models (LLMs) stepped into the kitchen with me. LLMs are a type of artificial intelligence that have been trained on a massive dataset of text (and code), including a vast trove of recipes; meaning that they can do so much more than just finding a suitable recipe. They can literally become your culinary genuis on demand.
So, how does it all come together? In this article, I'll detail how I:
- Developed an LLM app utilizing GPT-3.5 turbo LLM to assess available ingredients and recommend recipes
- Publish and deploy the LLM app on Agenta for production, enabling integration into a user interface for seamless communication via my mobile device
- Conducted human evaluations to ensure that the uploaded test set aligns with my specific needs