This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.

Indexation des fichiers de décès publiés par l'INSEE

Building RAG Applications with Haystack 2.0 published by Packt

Database Scalability using indexing, partition & sharding with PostgreSQL

XQuery provides decentralized access to indexed data for EVM blockchains such as Ethereum and Avalanche.

Password manager with Lit for encryption and Ipfs for storage

The Bastard Parser (a flexible hierarchical configuration parser)

SPIMI Ranked Retrieval Implementation and API

1D intervals incremental inverted index

Information retrieval toolkit for large document collections.

A pipeline to index and search through quiz questions.

A high-performance data ingestion and search tool designed to handle large-scale datasets efficiently using ScyllaDB. This project provides a robust solution for processing, storing, and querying large CSV and TXT files with optimized memory usage and concurrent processing capabilities.

Databases 2 - Project 2: Single-Pass In-Memory Indexing for information search and recovery

A URL shortener application built with Spring Boot and MongoDB. SnipNest allows users to easily shorten, manage, and track their URLs, providing a simple and efficient way to share links.

Red Black tree with filters for indexing.

Text Indexation & Query Algorithms Playground

NOZ is a distributed search engine program that can efficiently partition and distribute index data, implement dynamic indexing, handle high query loads, and provide fault tolerance mechanisms to ensure reliable performance.

PHP client StopWords for Portuguese Brazilian Language