This Github repository contains the code for a search engine developed as part of a university project. The goal of the project was to create a functional search engine that is able to return relevant results for a Wikipedia-based corpus.
- The search engine uses techniques for indexing and retrieval of information, including the use of Cosine Similarity and BM25 as well.
- The search engine was optimized for precision, and was evaluated using metrics such as Mean Average Precision at 40 (MAP@40), recall, and Mean Reciprocal Rank (MRR) to measure its performance.
- The search engine also has a feature for correcting spelling errors in queries in order to improve the results.
The index used in the final version of the search engine is available in the Google Storage Bucket "gs://316336338-index"