blog banner

Implement Document Information Retrieval Engine in Python

Document Information Retrieval Engine in Python

This application was built as an student project in Information Retrieval course at Azad Islamic University, NajafAbad branch. Indeed it is a document search engine that get query and shows the documents name of have the query.


  • Python3
  • nltk library
  • os library
  • math library
  • json library
  • tkinter library

after download the project you can copy your documents into the documents directory and run indexer.py to be create inverted index file and terms idf file by runing the search.py a window is open that you can write your query and see the results which are the name of documents that have your query and the cosine similarity number that represnt the similarity between that document and your query. for using the search enging without any UI you can run processor.py and use the search engin function.

This plugin is downloadable from my GitHub repository

Leave a Reply

Your email address will not be published. Required fields are marked *