SSD_S22_Project

VIDEO LINK - WORKING PROJECT

https://drive.google.com/file/d/1SWa2rYGu3FfgTMk6JKMv2dTPT1vpxWRc/view?usp=sharing

This repo is for the course project of Software Development course IIIT S22.

Dataset for this project is taken from
https://www.kaggle.com/datasets/Cornell-University/arxiv

Contributors:-

1. Lokesh Sharma
2. Piyush Singh
3. Mayush Kumar
4. Sumeet Agrawal

Motivation for this project is to create a fast Information Retrieval system of research papers using MERN Stack(UI), Elastic Search(retrieval) and Transformers(NLP).

1. Elastic Search
   1.1 Installation
   a. Download Elastic Search msi for windows.
   b. Start elastic search server as ".\bin\elasticsearch.bat"
   c. Reset elastic search password - .\bin\elasticsearch-reset-password.bat -u elastic.
   

   1.2 Test Elastic search API:

   https://localhost:9200/ssd-search/_mapping
   https://localhost:9200/ssd-search/_search
   https://localhost:9200/ssd-search/_search?pretty=true&q=:
   https://localhost:9200/ssd-search/_count
   

   1.3 Search using POSTMAN

   Sample query to Search (Not the vectorised embeddings) nyc-restaurants/_search {
   "query": {
   "match": {
   "_id": "50127304"
   }
   }
   

2. Using Faiss Run main.py

Testing using postman
POST http://localhost:8000/predict
{
"data": "Polymer Quantum Mechanics and its Continuum Limit A rather non-standard quantum representation of the canonicale"
}