Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/LightRAG
Library/LightRAGForked

HKUDS/LightRAG

LightRAG

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

View on GitHub↗Upstream HKUDS/LightRAG↗

Builder

HKUDS

HKUDS

HKUDS • individual

Stars

35,650

Using upstream star count

Forks

5,031

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Oct 2, 2024

Project creation date

README Summary

<div style="margin: 20px 0;"> <img src="./assets/logo.png" width="120" height="120" alt="LightRAG Logo" style="border-radius: 20px; box-shadow: 0 8px 32px rgba(0, 217, 255, 0.3);"> </div>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Entity Relationship ExtractionGraph-based Information RetrievalHybrid Search SystemsInformation Retrieval SystemsKnowledge Graph ConstructionLarge Language Model IntegrationNatural Language ProcessingRetrieval-Augmented GenerationVector Database Management

Tags

Entity Relationship ExtractionGraph-based Information RetrievalHybrid Search SystemsInformation Retrieval SystemsKnowledge Graph ConstructionLarge Language Model IntegrationNatural Language ProcessingRetrieval-Augmented GenerationVector Database ManagementAPIAWS BedrockAzure AICachingContext EngineeringDatabaseDockerDocument ProcessingEmbeddingsEvalsForkedGoogle AIGraphRAGHuggingFaceHybrid SearchKnowledge GraphLLM ServingLangfuseLarge Language ModelsLiteLLMLlamaIndexMilvusMultimodal AINumPyOllamaOpen WebUIOpenAIPrompt EngineeringPythonQdrantQwenRAGRAGASReal-Time / StreamingRerankingResearch / PapersStatisticsTransformersTutorialVector DatabasepgvectorvLLM

Taxonomy

AI Trends

Compound AI SystemsKnowledge-Enhanced AIGraph Neural NetworksHybrid Retrieval SystemsRAG Optimization

category

RAG & RetrievalFoundation ModelsAI AgentsEvals & BenchmarkingInference & ServingMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesData Science & Analytics

Deployment Context

Self-hostedCloud APIOn-premise

Industries

EducationLegal TechHealthcareResearch and AcademiaKnowledge ManagementContent Management

Modalities

Text

Skill Areas

Retrieval-Augmented GenerationKnowledge Graph ConstructionVector Database ManagementGraph-based Information RetrievalLarge Language Model IntegrationEntity Relationship ExtractionHybrid Search SystemsNatural Language ProcessingInformation Retrieval Systems

tag

APIAWS BedrockAzure AICachingContext EngineeringDatabaseDockerDocument ProcessingEmbeddingsEvalsForkedGoogle AIGraphRAGHuggingFaceHybrid SearchKnowledge GraphLLM ServingLangfuseLarge Language ModelsLiteLLMLlamaIndexMilvusMultimodal AINumPyOllamaOpen WebUIOpenAIPrompt EngineeringPythonQdrantQwenRAGRAGASReal-Time / StreamingRerankingResearch / PapersStatisticsTransformersTutorialVector DatabasepgvectorvLLM

Use Cases

Document Question AnsweringKnowledge Base SearchResearch Paper AnalysisTechnical Documentation QueryEducational Content RetrievalEnterprise Knowledge Mining

Recent Activity

Updated 3 months ago

7 Days

0

30 Days

0

90 Days

0

Merge branch 'postgres_vector_on_demand'

yangdx • Feb 9, 2026

c884d7d

Fix vector config check to respect enable_vector flag

yangdx • Feb 9, 2026

6c00af4

Fix vector config parsing and defer validation to connection time

yangdx • Feb 9, 2026

87e1049

Quality

research
Quality
high
Maturity
research

Categories

RAG & RetrievalPrimaryEvals & BenchmarkingInference & ServingMLOps & InfrastructureDev Tools & AutomationCloud & PlatformsLearning ResourcesData Science & AnalyticsFoundation ModelsAI AgentsMultimodal AIEdge & Mobile AISearch & KnowledgeOther AI / ML

PM Skills

Cost & EfficiencyUser ExperienceScale & ReliabilityData & EvaluationProduct DiscoveryDeveloper PlatformAI-Native Architecture

Languages

Python100.0%

Timeline

Project created
Oct 2, 2024
Forked
Feb 17, 2026
Your last push
3 months ago
Upstream last push
16 days ago
Tracked since
Feb 12, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…