Back to Arena
Supabase Vector
by Supabase Inc.
System Card
OrganizationSupabase Inc.
Released2023-02
Architecturevector-rag / managed pgvector on serverless Postgres
DetailsSupabase Vector is a managed PostgreSQL layer that ships pgvector as a first-class feature, exposing vector storage and HNSW/IVFFlat indexing through the standard Postgres wire protocol. The Vecs Python client abstracts collection management. Tightly integrated with Supabase Edge Functions, Storage, and Auth, enabling full-stack AI apps on a single platform.
Parameters—
Domainrag-retrieval
Open SourcePartial
WebsiteVisit
PostgreSQLpgvectorserverlessopen-source-backendfull-stack
Capability Profile
Benchmark Scores
5 of 14 benchmarksMulti-Turn Recall0/2
LoCoMo
no dataMemoryBank
no dataCross-Session Memory0/1
LongMemEval
no dataMulti-Hop QA2/3
Agent Task Memory0/1
AgentBench-Mem
no dataPersonalization0/1
PerLTQA
no dataFactuality / Grounding1/1
Sources:Supabase Vector vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Supabase Vector vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Supabase Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Supabase Vector vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)Supabase Vector vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)