Quivr

by QuivrHQ

System Card

OrganizationQuivrHQ

Released2023-05

Architecturevector-rag / "Second brain" opinionated RAG

DetailsPython RAG framework with YAML-defined workflows, pgvector / Faiss stores, Megaparse ingestion, multi-LLM. Personal "second brain" with per-brain memory.

Parameters—

Domainrag-retrievalpersonalization

Open SourceYes

WebsiteVisit

CodeRepository

second-brainmegaparseyamlpersonal

Capability Profile

Benchmark Scores

6 of 14 benchmarks

Long-Context Retrieval

1/5

RULER

no data

NIAH

no data

LooGLE

no data

LongBench

603p

∞Bench

no data

Multi-Turn Recall

2/2

LoCoMo

55.34p

MemoryBank

6411p

Cross-Session Memory

1/1

LongMemEval

60.614p

Multi-Hop QA

2/3

BABILong

no data

MultiHop-RAG

60.45p

HotpotQA

64.729p

Agent Task Memory

0/1

AgentBench-Mem

no data

Personalization

0/1

PerLTQA

no data

Factuality / Grounding

0/1

RAGAS

no data

Sources:Quivr (QuivrHQ/quivr); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Quivr (QuivrHQ/quivr); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Quivr (QuivrHQ/quivr); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Quivr (QuivrHQ/quivr); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Quivr (QuivrHQ/quivr); evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Quivr (QuivrHQ/quivr); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)