Running Prototype

Model

1. clone this repo.

   git clone https://github.com/dksath/QuoraQuestionPair
   

2. Download the model weights from Releases

3. Unzip file and add model folder into the repo

FastAPI

To run the model in the prototype, install FastAPI and uvicorn server. More information at FastAPI official website.

1. Install dependenices: - FastAPI - Uvicorn - TensorFlow - pandas - transformers (HuggingFace) - numpy

   Install dependenices by Anaconda:

   conda install -c conda-forge fastapi uvicorn
   

   Or, Install dependenices by pip:

   pip install fastapi "uvicorn[standard]"
   

   Or install relevant dependencies from requirements.txt:

   pip install -r requirements.txt

2. run the backend server :

   uvicorn main:app 

React

1. Install node.js and npm.

   You’ll need to have Node 14.0.0 or later version on your local development machine (but it’s not required on the server). We recommend using the latest LTS version. You can use nvm (macOS/Linux) or nvm-windows to switch Node versions between different projects. For more information visit the official website of node.js

2. Install dependency axios

   Install dependenices by npm:

   npm install [<package-spec> ...]
   
   aliases: add, i, in, ins, inst, insta, instal, isnt, isnta, isntal, isntall

3. change directory into react folder and start the server

   npm start