The Document Similarity and Deduplication Tool is made to solve the problem of having much repeated data in digital storage. Every day more and more documents are being. When there are duplicate or almost duplicate files it takes up space that is not needed and makes it hard to manage the data. The Document Similarity and Deduplication Tool uses Natural Language Processing techniques to prepare the text so the documents can be compared and analyzed correctly. The Document Similarity and Deduplication Tool system uses ways to measure how similar things are, like Cosine Similarity, Jaccard Index and Euclidean Distance to figure out how similar the documents are to each other. When the Document Similarity and Deduplication Tool finds documents it gives the user choices about what to do with them. The user can merge the documents put them in an archive or delete them depending on what the user wants and this makes the data cleaner and uses storage space. The Document Similarity and Deduplication Tool has a web interface that uses HTML, CSS and JavaScript. It lets the user upload files see how similar they are and manage the duplicates easily all in one place.