Project

AI Diet and Meal Planner

Medium

42 completions

~ 5 hours

4.6

In this project, you'll design multi-agent workflows via REST APIs by using FastAPI to structure, validate, and expose agent services. You'll interact with LLM providers using prompts, implement prompt engineering techniques and orchestrate LLM-based agents.

Provided by

JetBrains Academy

About

We all love a well-cooked home meal, but the choice of what to prepare is the actual challenge — especially when you are short on time, ingredients, or ideas of what to have. What if you had an AI sous-chef of your own? You will develop a multi-agent AI system using FastAPI where each agent plays a role in designing the perfect recipe depending on what you have in your kitchen and your nutritional needs. You’ll create agents that analyze available ingredients, filter recipes by diet type, and plan a complete step-by-step meal—with structured JSON outputs from LLMs.

Graduate project

This project covers the core topics of the Introduction to AI Engineering with Python course, making it sufficiently challenging to be a proud addition to your portfolio.

At least one graduate project is required to complete the course.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:

Initialize your FastAPI application environment, define the basic routing structure, and ensure your server can successfully handle HTTP requests. This foundational stage guarantees a reliable, testable environment before adding complexity.

Implement your first two AI agents: Inventory Agent and Diet Agent to validate and filter user-provided ingredients according to dietary preferences. Connect these Agents to an LLM via structured JSON-format prompts to ensure reliable, structured responses.

Develop the Manager Agent to orchestrate interactions between Inventory Agent and Diet Agent. Create a unified workflow (POST /ask) that seamlessly handles multiple agent interactions, simplifying the user experience by combining multiple steps into a single request.

Create the PlannerAgent to transform basic meal suggestions into fully detailed, structured cooking recipes. Implement structured prompts to ensure consistent and reliable JSON responses, and expose endpoints (/plan and /recommend) to deliver complete recipes directly to users.

Prepare your AI Diet & Meal Planner for production deployment by adding structured logging for observability and Docker containerization for portability and consistency. Ensure your application is ready for real-world environments.

Reviews

Eugene June

1 month ago

5.0

It was an awesome project, and I really enjoyed working on it. I learned how to build a FastAPI service where several agents collaborate to create recipes. Besides that, I learned how to structure a backend cleanly, work with LLMs, and package everything with Docker. It wasn't always smooth sailing, ...

Sebastian Müller

2 months ago

4.7

A fantastic project! Working on it gave me practical, real-world experience. I especially valued Pydantic validation for clean data models, multi-agent orchestration, structured logging, and Docker containerization to tie it all together.

GINO PAUL GONZALES CUSTODIO

5 months ago

4.0

He aprendido a trabajar con Docker desde un enfoque práctico, comprendiendo la construcción de imágenes mediante Dockerfiles, el uso correcto de instrucciones como FROM, ENV, ARG, COPY, WORKDIR, ENTRYPOINT y EXPOSE, y cómo influyen en el comportamiento del contenedor. También reforcé conceptos sobr ...

4.6

Learners who completed this project within the Introduction to AI Engineering with Python course rated it as follows:

Usefulness

4.7

Fun

4.6

Clarity

4.4