Skip to content

Provides personalized diet and workout recommendations based on user input. The recommendations are generated using a language model (LLM) for a more interactive experience.

Notifications You must be signed in to change notification settings

morganm94/Diet-Recommender

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Personalized Diet and Workout Recommender App

Overview

This is a web application designed to provide personalized diet and workout recommendations based on user input. The recommendations are generated using a language model (LLM) for a more interactive experience.

Features

  • User Input: Collects user information such as age, gender, weight, height, dietary preferences, address, and food allergies.

  • LLM Integration: Utilizes a language model for generating recommendations tailored to user input.

  • Recommendation Categories: Provides recommendations for restaurants, breakfast, dinner, and workouts.

  • Interactive Interface: Utilizes the Streamlit framework to create a user-friendly and interactive web interface.

Website Link

https://diet-recommender.streamlit.app

Getting Started

  1. Install the required dependencies if using Llama2 LLM:

    pip install torch streamlit transformers ctransformers

(OR) Set up your OpenAI API key:

Obtain an API key from OpenAI and set it as an environment variable.

```bash
export OPENAI_API_KEY=api_key
```
  1. Run the Streamlit app:

    streamlit run app.py

Usage

  1. Open the web application in your browser.

  2. Input your personal details including age, gender, weight, height, dietary preferences, address, and food allergies.

  3. Click the "Get Recommendations" button.

  4. View the personalized recommendations for restaurants, breakfast, dinner, and workouts.

Contact

Do you have any concerns or need any support? Just contact mmastrangelo1120@gmail.com for the communication.

About

Provides personalized diet and workout recommendations based on user input. The recommendations are generated using a language model (LLM) for a more interactive experience.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages