Radau tiesą.

DORA Graph RAG prototypes

Two competing approaches over the same EU Regulation 2022/2554 (DORA) corpus — Graph RAG vs Jev-reranked RAG. Quick, shareable, no auth / no database.

How it works

Both prototypes share the same first step: MiniSearch runs a BM25-style keyword search over the DORA corpus and returns a short shortlist (about 12 passages for Graph, about 15 for Jev). That shared gatekeeper keeps recall cheap and offline. From there the paths diverge. Graph RAG expands the shortlist with a one-hop walk over a static cites / covers graph built once from the regulation (structure, not embeddings), adding up to eight neighbours (hard cap — early BM25 hits consume the quota first). Jev does not expand at all: it scores each shortlisted passage for relevance and reorders the same fifteen candidates (15 in → 15 out).

1. Sequence

2. Pipeline fork

3. Candidate volume (Sankey)

Illustrative volumes: Graph expands (12 seeds → up to ~20 with graph extras); Jev reorders only (15 → 15). The static graph contributes the extra Graph flow; Jev volume stays flat.

Quick comparison

AspectGraph RAGJev-reranked RAG
Shared gatekeeperMiniSearch BM25-style keyword recall
Shortlist size~12 seeds~15 candidates
Next step1-hop expand on static cites/covers graphScore + reorder via /api/rerank + Jev
Candidate volumeGrows (~12 + up to ~8 extras → ~20)Flat (15 in → 15 out)
Graph / modelStatic regulation structure (not embeddings)TypeSafe Jev relevance scores
Runtime needsFully offline in the browserAPI key (OpenRouter / AI Gateway)

Sample queries

Chips on each prototype page also fire these queries.

Jev finding

Jev works well as a relevance reranker on DORA passages: structured score criteria (Irrelevant → Directly answers) give calibrated rankings without a generative LLM. Pair it with cheap keyword recall for a practical RAG stack.

Hosted at radau.tiesa.tech · tiesa.tech