Automated README summary
Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Vector Graph RAG is a Python library for multi-hop question answering over knowledge-intensive domains. It encodes entities and relations as vectors in Milvus, enabling subgraph expansion and retrieval without a graph database.
How it uses Jev
In the two-stage Jev retrieval mode, Jev Noul judgments score candidate relations; a configurable threshold is applied before retrieving their linked documents. The README does not specify the exact state or how scores are consumed in code.
Primitives:noul
Technique worth stealing
Two-stage Jev scoring of relations before passage retrieval, reaching the quality–latency Pareto frontier.
Try it
pip install vector-graph-rag, set OPENAI_API_KEY, then use VectorGraphRAG().rebuild_texts() and .query().
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.30
- Shows a System One patternnot found in the excerpt0.39
- Describes handling uncertaintyunclear0.51
- Reports measured numbersnot found in the excerpt0.11
- Is a runnable toolFound in material0.65
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelunclear0.53
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 2
- About JevFound in material0.84
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 16 Oct 2026.