Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.

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

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

Sentence-Transformers Information Retrieval example on Chinese

An overview of popular reranking models and architectures for 2 stage RAG pipelines

Dual Cross Encoder for Dense Retrieval

Livebook to run a Phoenix_LiveView documentation Retrieval-Augmented Generation (RAG) enhanced LLM

ARLC 2026 Agentic RAG Legal Challenge — Legal QA pipeline for DIFC court documents. Hybrid BM25 + vector retrieval, cross-encoder reranking, answer-grounded page verification.

Semantically Search Emojis From the Command Line!

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking (Findings of EMNLP 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

Free Perplexity-style web search library for local sLLM. Bing + DuckDuckGo → semantic filtering → reranking → LLM-ready prompt with citations.

Memory-aware context engine for AI coding agents — up to 91% fewer tokens, 17/18 rank-1 across 6 OSS projects. MCP-native, multi-repo, with persistent observations & decisions.

Docker image to run a self-hosted text embeddings and reranking server powered by Hugging Face TEI, with an OpenAI-compatible API. Supports BGE, Nomic, MiniLM and other models. Features optional reranking via cross-encoder models, API key auth, model management, offline/air-gapped mode, and persistent model cache.

Semantic Emoji Search Plugin for FiftyOne

🚀 Production-ready modular RAG monorepo: Local LLM inference (vLLM) • Hybrid retrieval with Qdrant • Semantic caching • Docling document parsing • Cross-encoder reranking • DeepEval evaluation • Full observability with Langfuse • Open WebUI chat interface • OpenAI-compatible API • Fully Dockerized

FastAPI backend for archive.ire.org

Score your resume against any number of jobs locally — free, explainable, CPU or GPU. Powered by a 156M ModernBERT cross-encoder.

Research benchmark: conversational memory learning on a corrected LoCoMo dataset