Fast and extendible Node.js/Javascript fulltext search engine.

The "smartest" OO Card Game Library

RagE (RAG Engine) - A tool supporting the construction and training of components of the Retrieval-Augmented-Generation (RAG) model. It also facilitates the rapid development of Q&A systems and chatbots following the RAG model.

⚡ A Crawler-based search engine that demonstrates the main features of a search engine (web crawling, indexing and ranking) and the interaction between them using Java and a Web Interface.

Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines: Employs Diversity, Lost-in-the-Middle, and Similarity rankers to reorder documents and maximize LLM context window performance. Implements Hybrid Retrieval with Reciprocal Rank Fusion (RRF) and rigorous BEIR evaluation (NDCG, MAP, Recall, Precision).

Search engine implemented with Java including: web crawling, indexing and ranking and the interaction between them.

Crawler based search engine that demonstrates the main features of a search engine (web crawling, indexing and ranking) and the interaction between them.

Modular LLM ranking library for Information Retrieval and RAG. Implements state-of-the-art Pairwise, Setwise, and Listwise ranking with structured generation and specialized models (RankZephyr, RankLlama). Features efficient sorting algorithms, sliding windows, and zero-shot capabilities. Built for Haystack pipelines.

A Crawler- based search engine that demonstrates the main features of a search engine (web crawling, indexing, ranking, Phrase Searching, Query Processing and Web Interface)

Pairwise Ranking Prompting (PRP): Zero-shot LLM reranking library implementing efficient pairwise strategies (Heapsort, Sliding Window, All-Pairs). Mitigates position bias via bidirectional comparison and ensures reliability with structured Pydantic validation. Built for Haystack pipelines.

🔎 A simple Crawler-based search engine that demonstrates the main features of a search engine (web crawling, indexing and ranking) and the interaction between them using Java and a Web Interface.

Domain adaptation in open domain question answering is tackled through theme specific rankers. We also propose a novel resource allocation algorithm to select the number of paragraph to be examined for extracting the answering. Finished 1st among participating IITs in Inter IIT tech Meet 11.0

A simple Crawler-based search engine that demonstrates the main features of a search engine.

R script used for the preparation of the initial input file, i.e. merging of various studies by logFC (LogFC),

A light weight NPM module to rank data.

Media ranker with a recommender system

My preferred method for sorting lists by user preference. A potentially more accurate albeit much slower method is Elo Sort.

💻🔎Search engine implemented with Java including: web crawling, indexing and ranking and the interaction between them.

Python scripts that grabs users ratings from the USCF website and then writes them to a google sheet