Back to Arena

Verba

by Weaviate

System Card

OrganizationWeaviate
Released2023-10
Architecturevector-rag / End-to-end RAG on Weaviate
Details"Golden RAGtriever" reference app with React frontend + Python backend. Multiple vector DBs (Weaviate primary), multi-LLM, multi-embedding, semantic/token/recursive chunking.
Parameters—
Domainrag-retrieval
Open SourceYes
WebsiteVisit
CodeRepository
weaviatereference-appchunkingstreamlit-like

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
664p
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
0/1
LongMemEval
no data
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
62.310p
HotpotQA
61.416p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
6524p
Sources:Verba (weaviate/Verba); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Verba (weaviate/Verba); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Verba (weaviate/Verba); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Verba (weaviate/Verba); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)Verba (weaviate/Verba); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)