Search

State-of-the-Art Embeddings, Retrieval, and Reranking

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

High-performance LLM, VLM, embedding, reranking, and audio inference for Apple Silicon, NVIDIA CUDA and AMD ROCm systems.

RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

Rust library for generating vector embeddings, reranking locally!

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

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.

Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.