A highly efficient, isomorphic, full-featured, multilingual text search engine library, providing full-text search, fuzzy matching, phonetic scoring, document indexing and more, with micro JSON state hydration/dehydration in-browser and server-side.

dead simple document index and search, nothing fancy

This repository highlights my learning journey in building Retrieval-Augmented Generation (RAG) pipelines using DeepSeek on Lightning AI, covering document ingestion, retrieval, and integration with generative AI. It showcases fine-tuning, evaluation, and optimization for accurate open-domain QA and knowledge management.

An AI-powered solution for efficient document querying. It uses Llama Index for vector-based indexing and OpenAI's GPT to interpret natural language queries, providing accurate search results.

Educational Document Base prototype to perform queries based on similarity and dissimilarity measures of documents to which stemming, lemmantization and latent semantic indexing was applied.

The purpose of this project is also to compare the efficiency and performance of two different methods for handling search operations: the inverted index and the term-document matrix

Programa que simula um algoritmo de indexação de documentos similar ao do Google. Ele é capaz de identificar ocorrências de termos em arquivos TXT.

Open Source Search Engine with built-in web/document crawler and an indexing method.

It is a search engine that uses json files as corpus of data.

Implementation of Document Indexing as part of COMP34711: NLP

A high-performance PDF document search application that extracts text from PDF files, indexes content using Whoosh, and provides a premium user interface with modern design elements. Features include context-aware search results, content highlighting, multi-format export options, and an interactive document viewer with match navigation.