https://github.com/ganbnuray/somm

Since 1969, only 279 people have become Master Sommeliers, highlighting the difficulty of the exam. Our AI sommelier, powered by RAG (Retrieval-Augmented Generation), makes it easier by giving you wine recommendations based on your taste. Whether you’re a wine expert or just enjoy a glass now and then, we’ll help you find the perfect bottle.
https://github.com/ganbnuray/somm

ai-recommendation-system clerk javascript jupyter-notebook material-ui nextjs openai-api pandas pinecone python rag react retrieval-augmented-generation wine

Last synced: 3 months ago
JSON representation

Since 1969, only 279 people have become Master Sommeliers, highlighting the difficulty of the exam. Our AI sommelier, powered by RAG (Retrieval-Augmented Generation), makes it easier by giving you wine recommendations based on your taste. Whether you’re a wine expert or just enjoy a glass now and then, we’ll help you find the perfect bottle.

• Host: GitHub
• URL: https://github.com/ganbnuray/somm
• Owner: ganbnuray
• Created: 2024-08-21T14:29:41.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-11-01T15:12:53.000Z (8 months ago)
• Last Synced: 2025-01-27T12:14:03.507Z (5 months ago)
• Topics: ai-recommendation-system, clerk, javascript, jupyter-notebook, material-ui, nextjs, openai-api, pandas, pinecone, python, rag, react, retrieval-augmented-generation, wine
• Language: Jupyter Notebook
• Homepage: https://sommelierai.vercel.app/
• Size: 59.7 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
![Somm Repo Banner](/public/banner.png)

# 🍷Somm🍷

> Since 1969, only 279 people have become Master Sommeliers, highlighting the difficulty of the exam. Our AI sommelier, powered by RAG (Retrieval-Augmented Generation), makes it easier by giving you wine recommendations based on your taste. Whether you’re a wine expert or just enjoy a glass now and then, we’ll help you find the perfect bottle.

## Inspiration

After watching Somm (2012), a documentary about master sommeliers and their examination process, I was inspired to create a RAG chatbot that could identify wines the user would like, just like a master sommelier. Finding a dataset that aligned with this exact inspiration was the starting point for my project.

## Demo

You can watch the demo video (sommdemo.mp4) in the public directory. Alternatively you can watch it in Youtube [here](https://youtu.be/S0NZxtXVKHw).

## Installation

### Online

You can use the live site at [Somm](https://sommelierai.vercel.app/).

### Local

To run the project locally, follow these steps:

1. **Clone the repository**:

   ```bash

   git clone https://github.com/ganbnuray/somm.git

   cd somm

   ```

2. **Run the development server**:

   ```bash

   npm run dev

   # or

   yarn dev

   # or

   pnpm dev

   # or

   bun dev

   ```

3. **Open your browser**:

   Navigate to http://localhost:3000 to see the result.

## Tech Stack

- ![Pandas](https://img.shields.io/badge/pandas-%23150458.svg?style=flat&logo=pandas&logoColor=white): Sampling the Kaggle wine reviews data

- ![Python](https://img.shields.io/badge/python-3670A0?style=flat&logo=python&logoColor=ffdd54) and ![Jupyter Notebook](https://img.shields.io/badge/jupyter-white?style=flat&logo=jupyter&logoColor=f37726): Creating vector embeddings

- ![Pinecone](https://img.shields.io/badge/Pinecone-ffffff?style=flat&logo=pinecone&logoColor=black): Storing vector embeddings & similarity searches

- ![MUI](https://img.shields.io/badge/MUI-%230081CB.svg?style=flat&logo=mui&logoColor=white): UI components

- ![OpenAI](https://img.shields.io/badge/OpenAI-00A67E.svg?style=flat&logo=openai&logoColor=white): API calls & generating chat responses

- ![Next JS](https://img.shields.io/badge/Next-black?style=flat&logo=next.js&logoColor=white) and ![React](https://img.shields.io/badge/react-%2320232a.svg?style=flat&logo=react&logoColor=%2361DAFB): Functionalities and routing

- ![Clerk](https://img.shields.io/badge/clerk-%23000000.svg?style=flat&logo=clerk&logoColor=purple): User login & signups

- ![Vercel](https://img.shields.io/badge/vercel-%23000000.svg?style=flat&logo=vercel&logoColor=white): Deployment

## Other resources

- ![](https://img.shields.io/badge/kaggle-%23150458.svg?style=flat&logo=kaggle&logoColor=white): Getting wine reviews and & sampling

  

  [Kaggle Wine Dataset](https://www.kaggle.com/datasets/zynicide/wine-reviews)

  

  [Kaggle Notebook for Sampling](https://www.kaggle.com/code/nurayganbarova/wine-sampling/notebook)

Note: Given the substantial volume of data, I utilized a random sampling approach to get 100 wines to manage and use it effectively for this project.