SeekStorm - sub-millisecond full-text search library & multi-tenancy server in Rust

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Tested and profiled implementation of the OkapiBM25 algorithm. Install the npm package. Now at 80K downloads per year!

Tunable full text search engine in JavaScript that: (1) works natively on web apps like Express.js; (2) easy to customize (via BM25) to specific types of documents (e.g. tweets, scientifc journals); (3) is deployable on either the client-side or the server side.

A file search engine based on modern search engine algorithms and data structures

The project is an extension of the SENT2IMG application, where an attention mechanism is introduced to obtain precise captions and Okapi BM25 algorithm has been utilised to rank the captions.

𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 | 𝗖𝗦𝟲𝟬𝟬𝟵𝟮 | 𝗕𝗼𝗼𝗹-𝗦𝗲𝗮𝗿𝗰𝗵, 𝗥𝗮𝗻𝗸𝗲𝗿, 𝗪𝗼𝗿𝗱𝗡𝗲𝘁 𝗦𝘂𝗺𝗺𝗮𝗿𝗶𝘇𝗲𝗿

A two-stage information retrieval model using baseline TF-IDF model and refined BM25.

A search engine which takes keywords as queries and retrieves a ranked list of results

Parse HTML pages. Create inverted index. Search for pages

A search engine that takes keyword queries as input and retrieves a ranked list of relevant results as output. It scraps a few thousand pages from one of the seed Wiki pages and uses Elasticsearch for a full-text search engine.

A basic and intuitive Python module for (Vector Space) IR system. (Focuses on simplicity and understandability)

Lucene, Retrieval and scoring pages using BM25

Content specific search engine with the aim to retrieve movies information given the content of the user's query.

Repository containing the final project for the Information Retrieval course at DSSC Master Degree (UniTS).

A detailed study on enhancing the working of an Automated Question Generation & Answering system in a real-time environment. Also, the paper gives a glimpse of bringing this system to freeware like WhatsApp.

Buscador de man pages con modelo vectorial y BM25.

IR ranking system based on Okapi BM25 and blind feedback