ETL framework to index data for AI, such as RAG; with realtime incremental updates and support custom logic like lego.

Big Data and Machine Intelligence Course in Autumn 2019.

Patient Intake Form Extraction using llm

🌲 Improved Interval B+ tree implementation, in TS 🌲

This repository contains an application designed to recommend scientific papers that are most similar to a given input paragraph. The application uses the llama and weaviate libraries to achieve this.

A zero-dependency library of classes that make filtering, sorting and observing changes to arrays easier and more efficient.

Designed to store and retrieve high-dimensional data, such as embeddings, efficiently. It enables fast similarity searches by leveraging techniques.

System for Managing the data generated by the SEAGrid Science Gateway

A Subgraph-indexing-runtime that prioritises performance & cost efficiency

Time series analysis showing trend, seasonality, and periodicity decomposition; and forecasting using Facebook Prophet. The analysis makes extensive use of indexing data tools and of the Pandas and Datetime libraries.

BORDS is an open-access reaction search engine that leverages Google's Open Reaction Database to provide ultra-fast, comprehensive access to millions of chemical reactions. Built with a modern cloud stack, it streamlines reaction data extraction, transformation, and indexing for researchers in chemistry and related fields.

Python implementation of a TF-IDF/cosine based search engine