Minimal keyword extraction with BERT

A simple python implementation of the Maximal Marginal Relevance (MMR) baseline system for text summarization.

Merkle Mountain Range in python

The GPX Tracker plugin integrates with MMR (Meshtastic-Matrix-Relay) to log location data from Meshtastic devices into organized GPX files, enabling easy tracking and visualization of device movements over time.

DynED is a novel ensemble construction and maintenance approach for data stream classification that dynamically balances the diversity and prediction accuracy of its components.

Quick basic match making rating calculator

AWS Serverless Application Repository template for Tolling Vision ANPR/MMR infrastructure with Lambda custom resources, auto-scaling, JWT authentication, and WAF protection

Efficient matchmaking algorithm for a 5v5 team-based game. Balances teams based on player MMR, preferred roles, and waiting time. Handles large player pools and creates fair, competitive matches.

Grabs the current MMR and saves it along other information into a MariaDB instance

Python script that when executed regularly keeps track of large amount StarCraft 2 accounts on the 1vs1 ladder

Skill rating algorithms for Python

Multimodal RAG with Adobe PDF Extract, CLIP embeddings & MMR diversity. Interactive dashboard with evaluation metrics for document intelligence.

Examination of whether LLMs can maintain consistency over extended multiple text generation for 10 medical personas. 5 novel plausibility metrics proposed, and an ontology of common LLM errors.

This repository contains a module for query-focused summarization of discussion threads in the DISCOSUMO project.

The Customer Support Ticket Classification and Response System combines advance AI models with RAG to automate and elevate ticket categorisation and response generation. By leveraging multi-model integration, sentiment analysis, urgency detection, and vector-based retrieval, it delivers precise, context-aware responses and actionable insights.

Hybrid RAG for Thai ROV patch notes: normalize diffs → hybrid retrieve (BM25 + dense in Chroma, MMR, optional bge reranker) → citation-first answers via FastAPI with OpenAI/Ollama generators. | ระบบ RAG ภาษาไทยสำหรับแพตช์โน้ต ROV

Classical Machine-Learning Approach to the identification of mean-motion resonances

Syllabix is an AI-powered study companion that leverages RAG with Qdrant vector storage and SentenceTransformers embeddings. It uses Maximal Marginal Relevance (MMR) for smarter retrieval, optimized chunking for better context, and generates inline citations directly from your course materials to help you stay on top of your coursework

Sample Python application that demonstrates how to use Tolling Vision