Back to Arena

OpenSearch Vector

by OpenSearch Project (AWS-led)

System Card

OrganizationOpenSearch Project (AWS-led)
Released2021-01
Architecturevector-rag / Lucene-based distributed search with kNN
DetailsOpenSearch (forked from Elasticsearch 7.10 in 2021) includes native k-NN vector search via its k-NN plugin, supporting HNSW (FAISS and nmslib backends) alongside inverted-index full-text search. Supports script scoring, painless scripting, and neural sparse retrieval via BERT-style models. AWS manages it as Amazon OpenSearch Service.
Parameters—
Domainrag-retrieval
Open SourceYes
WebsiteVisit
LucenekNNFAISSfull-textAWS-managed

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
69.232p
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
63.217p
HotpotQA
62.220p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
6843p
Sources:OpenSearch Vector vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)OpenSearch Vector vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)OpenSearch Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)OpenSearch Vector vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)OpenSearch Vector vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)