v3.1.0 — LangChain integration, BEIR benchmarks, biomedical preset

What's new in v3.1.0

LangChain integration

VORTEXRAG now works as a drop-in BaseRetriever in any LangChain pipeline:

from integrations.langchain_retriever import VortexRAGRetriever

retriever = VortexRAGRetriever(domain="medical", top_k=5)
retriever.add_documents(your_docs)

# works with RetrievalQA, ConversationalRetrievalChain, LCEL, etc.
docs = retriever.invoke("What causes sepsis?")

BEIR benchmark evaluation script

Run VORTEXRAG against the full BEIR benchmark suite:

pip install beir
python benchmarks/eval_beir.py --datasets nq hotpotqa scifact

Biomedical domain preset

New biomedical domain (τ=0.32) tuned for PubMed/BioASQ literature retrieval — sits between scientific (0.30) and medical (0.35) in strictness.

Branch structure

• main — protected, stable
• dev — integration branch, all contributor PRs target this
• feat/* — feature branches

247 tests passing across Python 3.10–3.13

---

Paper: https://doi.org/10.5281/zenodo.20579702

VORTEXRAG v3.0 — 7-Layer RAG Framework (New DOI + ORCID + 7 Experiment Pages)

VORTEXRAG v3.0

DOI: https://doi.org/10.5281/zenodo.20579702
ORCID: 0009-0004-9777-7592
HuggingFace Demo: https://huggingface.co/spaces/vigneshwar234/VORTEXRAG

What's new in v3.0

• 7 new experiment sections added to the paper (~7 more pages)
• 10 new figures/tables: ablation line plots, τ sensitivity curve, CPG threshold sensitivity, retrieval quality P@k/R@k/MRR/NDCG, Pareto frontier (faithfulness vs latency), corpus scaling dual-axis, 3 qualitative pipeline traces (financial/medical/legal), human evaluation Likert ratings
• New Zenodo DOI: 10.5281/zenodo.20579702 (v3.0 preprint live)
• ORCID added to author block: 0009-0004-9777-7592
• Human evaluation: 4.5/5 Factual Accuracy, 4.3/5 Causal Coherence

Key Results

System	EM	F1	Faithfulness
VORTEXRAG	74.8	82.6	0.94
Self-RAG	68.4	77.1	0.81
CRAG	66.9	75.8	0.79
Naive RAG	61.2	69.4	0.71

How to run

```bash
git clone https://github.com/vignesh2027/VORTEXRAG
cd VORTEXRAG
pip install -r requirements.txt
python examples/basic_usage.py
```

Citation

```bibtex
@Article{vignesh2026vortexrag,
title = {VORTEXRAG: Vector Orthogonal Resonance-Tuned EXtraction RAG},
author = {Vignesh, L},
year = {2026},
doi = {10.5281/zenodo.20579702},
url = {https://doi.org/10.5281/zenodo.20579702}
}
```