reranking-mechanism

"Hierarchical Reinforcement Learning for Integrated Recommendation" (AAAI 2021) https://ojs.aaai.org/index.php/AAAI/article/view/16580

Code of zlyang's master dissertation for Chinese grammatical error correction.

An interactive tool for exploring and comparing 5 different document re-ranking techniques with real-time evaluation and visualization to improve the accuracy of RAG System.

This project will develop a NEPSE chatbot using an open-source LLM, incorporating sentence transformers, vector database and reranking.

ViSecRAG: A comprehensive Retrieval-Augmented Generation framework featuring semantic-aware data chunking, vector-based retrieval, and fine-tuned embedding models optimized for Vietnamese language security and information extraction tasks.

Drowning in documents? Stop searching and Start Chatting! Ask questions, get follow-ups, and generate summaries across multi-format documents using an advanced RAG system with OCR.

AI Document assistant

A multi model efficient RAG applicattion enriched with OpenAI and AnthropicAI. Powered by Huggingface, Transformeres, AWS and GitHub CICD.

Lightweight retrieval refinement for RAG systems, combining neural reranking, lexical relevance, structured constraint matching, and reproducible evaluation over frozen candidate pools.

A domain specific multiagentic medical rag on hypertension and diabetics used to generate care plans for the patients.

ResearchMind MCP Server gives AI assistants a local research brain with RAG, semantic search, arXiv integration, and persistent memory. Built with Python, ONNX Runtime, ChromaDB, and SQLite.

A Streamlit-based multilingual legal assistant that processes mining law PDFs, retrieves context using FAISS and Ollama RAG, and delivers answers with translation and audio output.

A powerful Retrieval-Augmented Generation (RAG) chatbot application built with JavaFX

Ongoing RAG learning code base which includes Advance RAG techniques and Flag Embeddings.

RAG interno com ingestão para Markdown, chunk de tabelas por período, busca híbrida TF-IDF+BM25 (RRF), reescrita de query, rerank/MMR, quality gate e agente extrativo. Responde só com frases do corpus e recusa se a evidência não fecha. Pronto para MCP.

ClinIQ transforms clinical documents into an intelligent Q&A system. Upload PDFs, DOCX, or TXT files and ask questions in plain English. Built with React, Flask, and ChromaDB, it uses AI-powered RAG with hybrid search (semantic + BM25), reranking, and OpenAI GPT models to deliver accurate, evidence-based answers with source citations.

research paper: Adaptive Carbon‑Aware Search Re‑ranking with Contextual Bandits