Systèmes de Graph RAG
For un framework RAG basé sur les graphes, the strongest matches are supermemoryai/supermemory (Supermemory is a knowledge graph engine and vector database), microsoft/graphrag (GraphRAG is a pipeline and retrieval engine that transforms) and hkuds/lightrag (LightRAG is a graph-based retrieval framework that explicitly combines). docker/genai-stack and infiniflow/ragflow round out the shortlist. Each is ranked by relevance to your query, popularity and recent activity.
Frameworks et outils open source pour construire des pipelines de RAG utilisant des sources de données de graphes de connaissances structurées.
Systèmes de Graph RAG
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- supermemoryai/supermemory
supermemoryai/supermemory
27,334Voir sur GitHubSupermemory is an artificial intelligence memory management platform designed to provide autonomous agents with persistent, long-term knowledge bases. It functions as a centralized repository that synchronizes multimodal data, enabling agents to maintain context and historical information across complex, multi-session workflows. By serving as a knowledge graph engine and vector database orchestrator, the platform ensures that information remains accessible and relevant for automated tasks. The system distinguishes itself through its hybrid indexing approach, which combines vector similarity s
Supermemory is a knowledge graph engine and vector database orchestrator with hybrid indexing, directly matching the need for a tool that combines knowledge graphs with RAG to query documents.
TypeScriptHybrid Vector-Graph DatabasesKnowledge Graph ConstructionKnowledge Graph Construction Tools - microsoft/graphrag
microsoft/graphrag
33,792Voir sur GitHubGraphRAG is a data processing pipeline and retrieval engine designed to transform unstructured text into interconnected knowledge graphs. By utilizing language models to extract entities and relationships, it builds structured representations of information that enable context-aware retrieval for downstream applications. The system distinguishes itself through hierarchical graph clustering and large-scale data synthesis, which organize massive document corpora into multi-level structures. This approach allows for both vector-based semantic searches and graph-based traversals, providing a comp
GraphRAG is a pipeline and retrieval engine that transforms unstructured text into knowledge graphs using LLMs and supports both vector semantic search and graph traversal for hybrid retrieval, making it a comprehensive and direct match for building a knowledge-graph-powered RAG system over documents.
PythonKnowledge Graph Construction ToolsGraph Query Interfaces - hkuds/lightrag
HKUDS/LightRAG
36,651Voir sur GitHubLightRAG is a graph-based retrieval framework designed to build retrieval-augmented generation pipelines. It structures unstructured text into knowledge graphs, enabling multi-hop reasoning and complex query synthesis across large document collections. By integrating dense vector embeddings with structured knowledge graphs, the system facilitates both similarity-based and relationship-aware information retrieval. The framework distinguishes itself through a dual-level retrieval strategy that combines low-level keyword matching with high-level semantic graph traversal to capture both specific
LightRAG is a graph-based retrieval framework that explicitly combines knowledge graph construction with dense vector embeddings and hybrid retrieval (graph vector), directly enabling the document querying over a collection with LLM integration that this search seeks.
PythonHybrid Vector-Graph DatabasesKnowledge Graph Retrieval - docker/genai-stack
docker/genai-stack
5,333Voir sur GitHubThis project is a containerized development stack and application framework for building retrieval-augmented generation systems. It provides a dockerized AI sandbox that integrates local model runtimes, knowledge graphs, and vector stores to enable the creation of contextual chatbots. The stack is distinguished by its graph-based vector store, which combines structured knowledge graphs with vector indices for both semantic and structural data retrieval. It allows for local model hosting with CPU or GPU acceleration, enabling generative tasks without reliance on external cloud APIs. The frame
This containerized stack integrates knowledge graphs with vector indices and local LLMs to build retrieval-augmented generation systems, hitting all your required features from document ingestion to hybrid graph–vector querying.
PythonHybrid Vector-Graph DatabasesVector Embeddings - infiniflow/ragflow
infiniflow/ragflow
82,922Voir sur GitHubThis project is a comprehensive retrieval-augmented generation platform designed for building, managing, and deploying knowledge-based AI applications. It provides a unified environment for organizing datasets, configuring conversational chat assistants, and developing autonomous agents that execute multi-step reasoning workflows. By integrating document intelligence with advanced retrieval pipelines, the platform enables the creation of grounded, verifiable responses supported by traceable citations. The platform distinguishes itself through deep document understanding and sophisticated know
RAGFlow is a comprehensive RAG platform that combines knowledge graph capabilities (GraphRAG) with vector retrieval and LLM integration, directly matching the need for a knowledge-graph-enhanced document querying system.
PythonKnowledge Graph ConstructionDocument Parsing PipelinesDocument Chunking Strategies - datawhalechina/all-in-rag
datawhalechina/all-in-rag
3,989Voir sur GitHubThis project is a retrieval augmented generation framework designed to build pipelines that connect unstructured data and knowledge graphs with large language models. It functions as a vector database orchestrator for indexing text and multimodal content, as well as a system for translating natural language queries into structured database commands. The framework integrates a hybrid retrieval engine that combines dense vector search with sparse keyword matching to increase the precision of retrieved contexts. It further enhances reasoning and relationship mapping through a graph-augmented ret
All-in-RAG is a RAG framework that explicitly connects unstructured data with knowledge graphs, integrates vector and hybrid retrieval, and supports LLM-based generation and natural-language-to-structured-query translation, covering the key capabilities of a knowledge-graph RAG system.
PythonRAG PipelinesDocument and Unstructured ExtractionGraph Knowledge Indexing - embedchain/embedchain
embedchain/embedchain
58,769Voir sur GitHubEmbedchain is an LLM memory management framework and RAG orchestration engine designed to provide AI agents with a persistent storage layer. It functions as a long-term memory pipeline that extracts facts from unstructured interactions and stores them as permanent knowledge base entries to retain user preferences and interaction history across sessions. The system employs a hybrid vector database interface that combines semantic embeddings with traditional keyword search. It utilizes an entity-linking knowledge graph to connect related information points and applies temporal ranking to distin
Embedchain is a RAG orchestration engine that combines hybrid vector search with an entity-linking knowledge graph and fact extraction pipelines, making it a direct fit for building a knowledge-graph-augmented RAG system that can ingest and query over documents.
PythonKnowledge Graph Retrieval
