raphaelmansuy/edgequake

EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation

What it solves

EdgeQuake is a high-performance Graph-RAG framework designed to overcome the limitations of traditional RAG, which relies solely on vector similarity. While vector search is effective for keyword lookups, it often fails at multi-hop reasoning and thematic queries. EdgeQuake solves this by transforming documents into a knowledge graph of entities and relationships, allowing the system to traverse both vector space and graph structures for superior retrieval and generation.

How it works

Built in Rust for high performance, EdgeQuake implements the LightRAG algorithm. It decomposes documents into a knowledge graph using LLM-powered entity extraction and relationship mapping. At query time, it uses a hybrid approach—combining vector search (via pgvector) and graph traversal (via Apache AGE) within a PostgreSQL database. It offers six different query modes, including Naive, Local, Global, and Hybrid, to balance latency and depth of reasoning.

Who it’s for

Developers and organizations needing a production-ready RAG system that can handle complex, relationship-based queries across large document sets, with support for multi-tenancy, authentication, and high concurrency.

Highlights

  • Knowledge Graph Engine: Uses Louvain clustering for community detection and multi-pass gleaning to increase entity extraction rates.
  • Hybrid RAG: Combines Personalized PageRank (PPR) graph walks with HNSW vector search for comprehensive results.
  • PDF Vision Pipeline: Supports both fast text extraction and a vision-based mode (using GPT-4o, Claude, or Gemini) to reconstruct complex tables and multi-column layouts.
  • Production-Ready Infrastructure: Features a REST API with SSE streaming, multi-tenant workspace isolation, and integration with the Model Context Protocol (MCP) for AI agents.
  • High Performance: Written in Rust, claiming significantly lower query latency and higher concurrency compared to traditional RAG implementations.

Related

  • Project
    HKUDS/LightRAG

    A lightweight, graph-based RAG framework that combines knowledge graphs and vector embeddings to provide efficient, high-quality retrieval and global context understanding.

  • Project
    automataIA/graphrag-rs

    A high-performance Rust implementation of GraphRAG that enables building knowledge graphs from documents for natural language querying across server, WASM, and hybrid deployments.

  • Project
    FalkorDB/GraphRAG-SDK

    GraphRAG‑SDK is a Python SDK that builds a knowledge graph in FalkorDB from your documents and then answers questions by traversing that graph. It adds provenance edges, multi‑hop retrieval, and optional abstention to dramatically cut down LLM hallucinations, and it ships with benchmarks showing it outperforms standard vector‑RAG. Install via pip, run a FalkorDB container, ingest texts (or PDFs/markdown), call `finalize()`, and query with `completion()`. The library supports schemas, incremental updates, custom providers, and is Apache‑2.0 licensed.

  • Project
    iMoonLab/Hyper-RAG

    A hypergraph-driven Retrieval-Augmented Generation (RAG) framework that reduces LLM hallucinations by capturing complex, beyond-pairwise relationships in domain-specific knowledge.

  • Project
    ggozad/haiku.rag

    An agentic, local-first RAG system that provides citation-aware answers to questions about documents, featuring multimodal search and sandboxed Python analysis.