query-rewriting

SearchBetter: query rewriting for search engines on small corpuses (Harvard research project)

[VLSP 2025] ViDRILL is a Vietnamese document retrieval system for VLSP 2025. It combines dense and sparse retrieval, reranking, and optional LLM-based query rewriting and reasoning to support high-accuracy information retrieval and future LLM-enhanced pipelines.

Advanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via Weaviate. Automates prompt tuning and few-shot selection using GEPA, SIMBA, MIPRO, COPRO, and BootstrapFewShot optimizers on datasets like FreshQA, HotpotQA, TriviaQA, Wikipedia and PubMedQA.

Implementation query expansion in semantic meta-search engine. The resulting expansion system is called Wiki-MetaSemantik.

It shows an advanced RAG with Reflection where LangGraph is used for workflow management.

한국어 ASR 질의를 DB 용어로 안전하게 정규화하는 Foundry-first bounded agent. 로컬 발음 후보, Ollama 옵션, V1 호환.

🚤 User and policy management component for KorAP, capable of rewriting queries for policy based document restrictions.

MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.

唐诗三百首RAG检索增强生成

SymSpellComplete, a typo-tolerant autocomplete library in Rust.

Production-quality AI search project exploring modern retrieval, reranking, RAG, fine-tuning, personalization and evaluation for travel search.

Self-RAG chatbot with LangGraph that retrieves from internal PDFs, verifies grounding (IsSUP), checks usefulness (IsUSE), and iteratively rewrites queries to improve answer quality.

ISWC'21 Post & Demo, A DBpedia-based Benchmark for Ontology-mediated Query Answering

Production LLMOps pipeline: Multi-Modal RAG with Azure Document Intelligence, Azure AI Search (hybrid retrieval + RRF), cross-encoder reranking, GPT-4.1 generation, and Azure AI Evaluation — served via FastAPI dashboard with Cosmos DB session tracking.

Production-grade Mixture-of-Experts (MoE) AI Assistant featuring Semantic Routing, Hybrid ML, Gemini, Groq & OpenAI orchestration, Live Web Search (Tavily/Serper), RAG, Explainable AI (XAI), an Answer Quality Engine, Voice AI, MongoDB persistence, and Dockerized deployment.

An open-source PoC of a 3-stage pipeline for medical semantic search, evaluated on the TREC-CDS 2016 dataset.

A comprehensive research project comparing different Retrieval-Augmented Generation (RAG) techniques applied to medical question-answering in obstetrics.

Autonomous RAG system with self-correcting retrieval, hallucination detection, and LangGraph orchestration. Features multi-iteration query rewriting, streaming responses, and comprehensive evaluation metrics.

MCTS for query rewrite

Building and Improving a Document RAG System for Marlowe & Finch customer support using LangChain, OpenAI, Chroma DB, and Query Rewriting.