Back to Arena

GraphRAG-SDK

by FalkorDB

System Card

OrganizationFalkorDB
Released2024-05
Architecturegraph-rag / Ontology-driven KG + multi-agent orchestration
DetailsWorkflow for ontology creation (auto or manual), KG construction on FalkorDB, and multi-agent chat sessions. Customizable Cypher-generation and QA prompts; LiteLLM-compatible.
Parameters—
Domainrag-retrievalknowledge-graph
Open SourceYes
WebsiteVisit
CodeRepository
falkordbontologymulti-agentcypher

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
68.321p
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
70.925p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
7579p
HotpotQA
69.542p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
70.351p
Sources:GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)