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.

Developed an AI-powered document intelligence platform for educators with Google Drive integration, enabling seamless processing of diverse document formats. Leveraged Qdrant vectorization and AzureOpenAI gpt-4o-mini to create a robust question answering system with optimized search capabilities, transparent citations, and direct source navigation.

Implementation of Document Indexing as part of COMP34711: NLP

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

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