RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.
Unified web search + content extraction extension for pi with 19 backends. Auto-fallback, RRF combine mode, targeted combine, pluggable web_read (Jina/Sofya/Firecrawl/Exa), and env/shell credential resolution.
Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines: Employs Diversity, Lost-in-the-Middle, and Similarity rankers to reorder documents and maximize LLM context window performance. Implements Hybrid Retrieval with Reciprocal Rank Fusion (RRF) and rigorous BEIR evaluation (NDCG, MAP, Recall, Precision).
Allows you to merge search results from multiple search engines using the reciprocal rank fusion algorithm.
A state-of-the-art Information Retrieval system for TREC ROBUST04 achieving MAP 0.3309. Features a Novel 4-Way RRF Fusion architecture combining BM25, Neural Reranking (Cross-Encoders), and LLM-Augmented Query Expansion (Query2Doc) via LiteLLM.
Analysis and implementational details of rank aggregation methods for combing results of multiple engines to achieve best mAP and P@5,10 values
This demo showcases a store associate application built on MongoDB Atlas, created to streamline product discovery and inventory visibility as part of a unified commerce strategy.
RAG-based interview assistant with hybrid dense+sparse retrieval, query routing, and source-cited answers grounded in real resume/project data.
Autonomous log-investigation engine retrieves evidence with hybrid BM25 + vector search (RRF + cross-encoder reranking) and drives an agent that reads, hypothesizes, and probes iteratively to surface root causes.
A high-performance Retrieval-Augmented Generation pipeline for technical Q&A workloads. Combines hybrid retrieval (dense + BM25), query expansion, Reciprocal Rank Fusion (RRF), and cross-encoder re-ranking to improve retrieval precision and answer grounding. Evaluated with Ragas, showing measurable gains in context recall and faithfulness.
Production-grade hybrid RAG: BM25 + dense retrieval + cross-encoder reranking + LLM-as-Judge
AI document assistant with a production RAG pipeline — hybrid BM25 + semantic search, cross-encoder reranking, and streaming answers. Built with FastAPI, Streamlit, ChromaDB, and DeepSeek LLM. Fully Dockerized and deployed on Railway.
Hybrid RAG with three retrievers—Lexical (BM25), Semantic (embeddings), and Hybrid (Reciprocal Rank Fusion) — parallel retrieval, Llama 3 generation, and side-by-side evaluation with reproducible notebooks.
Production-grade hybrid RAG with the parts demos skip: dense (Qdrant) + BM25 + hand-written RRF fusion + cross-encoder reranking, citation-verified generation (attribution measured, never declared), and a reproducible eval harness — recall@k · nDCG · MRR · paired bootstrap CI95 · RAGAS-style metrics. LangChain · LangGraph · FastAPI.
Defensive multi-stage AI agent that triages support tickets across HackerRank, Claude, and Visa using local RAG, hybrid retrieval, and structured reasoning. Escalates high-risk cases safely.
An AI-powered public grievance and complaint management platform built on the MERN stack. Features automated LLM-based priority routing, semantic search, and real-time dashboards for citizens and administrators.
A mvp product multi-stage search engine over MS MARCO (8.8M passages). BM25 + dense retrieval with RRF fusion, cross-encoder reranking, and FastAPI serving. Built with dependency injection, full test coverage (139 tests), and benchmark-validated evaluation (MRR@10: 0.3660).
LangChain vector store that combines BigQuery VECTOR_SEARCH and SEARCH for hybrid semantic + keyword retrieval
Add a description, image, and links to the reciprocal-rank-fusion topic page so that developers can more easily learn about it.
To associate your repository with the reciprocal-rank-fusion topic, visit your repo's landing page and select "manage topics."