vector-graph-rag 0.3.1__tar.gz → 0.4.0__tar.gz

{vector_graph_rag-0.3.1 → vector_graph_rag-0.4.0}/.env.example

@@ -36,7 +36,9 @@ MILVUS_URI=./vector_graph_rag.db
 # Model Configuration (Optional - uses VGRAG_ prefix)
 # ============================================================================
 # LLM model for triplet extraction and reranking
-# VGRAG_LLM_MODEL=gpt-4o-mini
+# GPT-6 uses Responses; other configured models use Chat Completions.
+# VGRAG_LLM_MODEL=gpt-6-luna
+# VGRAG_LLM_REASONING_EFFORT=medium
 
 # Embedding model (HuggingFace model name or OpenAI model name)
 # VGRAG_EMBEDDING_MODEL=facebook/contriever
@@ -101,9 +103,9 @@ MILVUS_URI=./vector_graph_rag.db
 # VGRAG_PASSAGE_COLLECTION=vgrag_passages
 
 # Task-specific models override the shared VGRAG_LLM_MODEL.
-# VGRAG_EXTRACTOR_MODEL=gpt-5-mini
+# VGRAG_EXTRACTOR_MODEL=gpt-6-luna
 # VGRAG_RERANKER_MODEL=jev
-# VGRAG_ANSWER_MODEL=gpt-4o-mini
+# VGRAG_ANSWER_MODEL=gpt-6-luna
 # TYPESAFE_API_KEY=your-key
 
 # VGRAG_JEV_MAX_CONCURRENCY=3

vector_graph_rag-0.4.0/.github/workflows/release.yml

@@ -0,0 +1,69 @@
+# Push a v-prefixed tag only after the release pull request passes validation.
+name: Validate and Publish Python Package
+
+on:
+  pull_request:
+    branches: [main]
+  push:
+    tags: ["v*"]
+
+permissions:
+  contents: read
+
+jobs:
+  validate:
+    name: Validate Python ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - name: Install test dependencies
+        run: uv sync --locked --python '${{ matrix.python-version }}' --extra dev --extra api
+      - name: Check package and tag versions
+        run: |
+          uv run --no-sync python - <<'PY'
+          import os
+          from importlib.metadata import version
+          from vector_graph_rag import __version__
+
+          package_version = version("vector-graph-rag")
+          assert package_version == __version__, (package_version, __version__)
+          if os.environ["GITHUB_REF_TYPE"] == "tag":
+              assert os.environ["GITHUB_REF_NAME"] == f"v{package_version}"
+          print(f"Validated version {package_version}")
+          PY
+      - name: Run tests
+        run: uv run --no-sync pytest tests -q
+      - name: Build distributions
+        run: uv build
+      - name: Verify wheel installation in isolation
+        run: |
+          uv run --isolated --no-project --python '${{ matrix.python-version }}' \
+            --with ./dist/vector_graph_rag-*.whl python -c \
+            'from importlib.metadata import version; from vector_graph_rag import Settings, VectorGraphRAG, __version__; assert version("vector-graph-rag") == __version__; print(__version__)'
+      - name: Save validated distributions
+        if: matrix.python-version == '3.12'
+        uses: actions/upload-artifact@v4
+        with:
+          name: distributions
+          path: dist/
+
+  publish:
+    name: Publish to PyPI
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
+    needs: validate
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: distributions
+          path: dist/
+      - name: Publish validated distributions
+        uses: pypa/gh-action-pypi-publish@release/v1

vector_graph_rag-0.4.0/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+## 0.4.0
+
+### What's changed
+
+- Default generation tasks now use GPT-6 Luna through Responses with medium reasoning: triplet extraction, entity extraction, relationship reranking and answer generation.
+- Cache keys distinguish the Responses interface and reasoning effort. Incomplete, refused or empty Responses outputs are rejected instead of cached as successful answers.
+- Retrieval evaluation now compares Jev with GPT-6 Luna and official DeepSeek V4.1 Flash. The report retains the September/October 2026 evaluation timeline, reproducible Jev evidence and a link to superseded experiments.
+- Publishing now requires passing tests on Python 3.10 and 3.12, matching package/tag versions, and an isolated wheel installation check.
+
+### Upgrading
+
+The default model changed from GPT-4o-mini to GPT-6 Luna. Custom OpenAI-compatible endpoints must support Responses when using GPT-6 models. Explicitly configured non-GPT-6 models retain Chat Completions; set `VGRAG_LLM_MODEL` explicitly to retain your chosen model. The OpenAI SDK minimum is now 1.66.0.
+
+Reasoning defaults to `medium` and can be configured with `VGRAG_LLM_REASONING_EFFORT`. Existing cache files are preserved, but GPT-6 Responses requests use separate cache keys. DeepSeek is an evaluation baseline, not the runtime default. Frozen benchmark results are unchanged by the runtime migration.

{vector_graph_rag-0.3.1 → vector_graph_rag-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: vector-graph-rag
-Version: 0.3.1
+Version: 0.4.0
 Summary: A Graph RAG implementation using pure vector search with Milvus
 Project-URL: Homepage, https://github.com/zilliztech/vector-graph-rag
 Project-URL: Documentation, https://zilliztech.github.io/vector-graph-rag/
@@ -23,7 +23,7 @@ Requires-Dist: httpx>=0.27
 Requires-Dist: langchain-core>=0.3.0
 Requires-Dist: milvus-lite<3,>=2.4.0
 Requires-Dist: numpy>=1.24.0
-Requires-Dist: openai>=1.0.0
+Requires-Dist: openai>=1.66.0
 Requires-Dist: pydantic-settings>=2.0.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: pymilvus<2.6.10,>=2.4.0
@@ -398,7 +398,7 @@ Before introducing Jev, we evaluated Vector Graph RAG on three multi-hop QA benc
 
 **Two-stage Jev reaches the quality–latency Pareto frontier.**
 
-**86.07% average Recall@5**, the highest among the compared methods, with **3.13 seconds of additional model-call latency**. On MuSiQue and 2Wiki (1,000 questions each), two-stage Jev reaches the Pareto frontier under the reference latency estimates. This two-dataset result is separate from the historical three-dataset average above.
+**86.07% average Recall@5**, the highest among the compared methods, with **3.13 seconds of additional model-call latency**. On MuSiQue and 2Wiki (1,000 questions each), two-stage Jev reaches the Pareto frontier using the displayed timings. This two-dataset result is separate from the historical three-dataset average above.
 
 ![Quality and additional model latency](docs/assets/evaluation/quality-latency.png)
 

{vector_graph_rag-0.3.1 → vector_graph_rag-0.4.0}/README.md

@@ -290,7 +290,7 @@ Before introducing Jev, we evaluated Vector Graph RAG on three multi-hop QA benc
 
 **Two-stage Jev reaches the quality–latency Pareto frontier.**
 
-**86.07% average Recall@5**, the highest among the compared methods, with **3.13 seconds of additional model-call latency**. On MuSiQue and 2Wiki (1,000 questions each), two-stage Jev reaches the Pareto frontier under the reference latency estimates. This two-dataset result is separate from the historical three-dataset average above.
+**86.07% average Recall@5**, the highest among the compared methods, with **3.13 seconds of additional model-call latency**. On MuSiQue and 2Wiki (1,000 questions each), two-stage Jev reaches the Pareto frontier using the displayed timings. This two-dataset result is separate from the historical three-dataset average above.
 
 ![Quality and additional model latency](docs/assets/evaluation/quality-latency.png)
 

{vector_graph_rag-0.3.1 → vector_graph_rag-0.4.0}/docs/architecture/design-philosophy.md

@@ -119,15 +119,11 @@ The key insight is that **vector search combined with subgraph expansion already
 
 With these three mechanisms working together, the candidate set is already rich and relevant. A single LLM reranking pass is sufficient to select the best relations from this high-quality pool.
 
-### The Cost Advantage
+### Model Calls and Cost
 
-Each LLM call adds latency (typically 1–3 seconds) and cost. For a system processing thousands of queries per day, the difference between 2 and 5 LLM calls per query is substantial:
+Avoiding an iterative retrieval loop reduces the number of dependent model calls. Actual latency and cost also depend on prompt size, output length, reasoning settings, provider queueing and request concurrency; call counts alone do not establish a speedup or cost reduction.
 
-| Metric | Iterative (5 calls) | Single-Pass (2 calls) | Savings |
-|--------|---------------------|----------------------|---------|
-| **Latency** | ~5–15s | ~2–6s | 2–3x faster |
-| **Cost** (GPT-4o-mini) | ~5x base | ~2x base | 60% cheaper |
-| **Cost** (GPT-4o) | ~5x base | ~2x base | 60% cheaper |
+See the [retrieval evaluation](../evaluation.md#jev-reranker-evaluation) for measured Jev, GPT-6 Luna and DeepSeek V4.1 Flash quality and model-call latency. Those retrieval measurements do not benchmark extraction or answer generation.
 
 > [!TIP]
 > For applications where latency and cost are secondary to accuracy on extremely complex queries (5+ hop chains, ambiguous entity resolution), iterative approaches may still be worth the overhead. See [When to Consider Alternatives](#7-when-to-consider-alternatives).

vector_graph_rag-0.4.0/docs/assets/evaluation/quality-latency.svg

@@ -0,0 +1,438 @@
+<?xml version="1.0" encoding="utf-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+  "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg xmlns:xlink="http://www.w3.org/1999/xlink" width="1080pt" height="612pt" viewBox="0 0 1080 612" xmlns="http://www.w3.org/2000/svg" version="1.1">
+ <metadata>
+  <rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+   <cc:Work>
+    <dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
+    <dc:format>image/svg+xml</dc:format>
+    <dc:creator>
+     <cc:Agent>
+      <dc:title>Matplotlib v3.11.2, https://matplotlib.org/</dc:title>
+     </cc:Agent>
+    </dc:creator>
+   </cc:Work>
+  </rdf:RDF>
+ </metadata>
+ <defs>
+  <style type="text/css">*{stroke-linejoin: round; stroke-linecap: butt}</style>
+ </defs>
+ <g id="figure_1">
+  <g id="patch_1">
+   <path d="M 0 612
+L 1080 612
+L 1080 0
+L 0 0
+z
+" style="fill: #ffffff"/>
+  </g>
+  <g id="axes_1">
+   <g id="patch_2">
+    <path d="M 97.2 495.72
+L 1047.6 495.72
+L 1047.6 110.16
+L 97.2 110.16
+z
+" style="fill: #ffffff"/>
+   </g>
+   <g id="matplotlib.axis_1">
+    <g id="xtick_1">
+     <g id="line2d_1">
+      <defs>
+       <path id="m1e54ec5eb8" d="M 0 0
+L 0 3.5
+" style="stroke: #000000; stroke-width: 0.8"/>
+      </defs>
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="123.198784" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_1">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="123.198784" y="511.837187" transform="rotate(-0 123.198784 511.837187)">0</text>
+     </g>
+    </g>
+    <g id="xtick_2">
+     <g id="line2d_2">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="238.748936" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_2">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="238.748936" y="511.837187" transform="rotate(-0 238.748936 511.837187)">2</text>
+     </g>
+    </g>
+    <g id="xtick_3">
+     <g id="line2d_3">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="354.299088" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_3">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="354.299088" y="511.837187" transform="rotate(-0 354.299088 511.837187)">4</text>
+     </g>
+    </g>
+    <g id="xtick_4">
+     <g id="line2d_4">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="469.84924" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_4">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="469.84924" y="511.837187" transform="rotate(-0 469.84924 511.837187)">6</text>
+     </g>
+    </g>
+    <g id="xtick_5">
+     <g id="line2d_5">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="585.399392" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_5">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="585.399392" y="511.837187" transform="rotate(-0 585.399392 511.837187)">8</text>
+     </g>
+    </g>
+    <g id="xtick_6">
+     <g id="line2d_6">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="700.949544" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_6">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="700.949544" y="511.837187" transform="rotate(-0 700.949544 511.837187)">10</text>
+     </g>
+    </g>
+    <g id="xtick_7">
+     <g id="line2d_7">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="816.499696" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_7">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="816.499696" y="511.837187" transform="rotate(-0 816.499696 511.837187)">12</text>
+     </g>
+    </g>
+    <g id="xtick_8">
+     <g id="line2d_8">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="932.049848" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_8">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="932.049848" y="511.837187" transform="rotate(-0 932.049848 511.837187)">14</text>
+     </g>
+    </g>
+    <g id="xtick_9">
+     <g id="line2d_9">
+      <g>
+       <use xlink:href="#m1e54ec5eb8" x="1047.6" y="495.72" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_9">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="1047.6" y="511.837187" transform="rotate(-0 1047.6 511.837187)">16</text>
+     </g>
+    </g>
+    <g id="text_10">
+     <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="572.4" y="527.838125" transform="rotate(-0 572.4 527.838125)">Additional model-call latency (s)</text>
+    </g>
+   </g>
+   <g id="matplotlib.axis_2">
+    <g id="ytick_1">
+     <g id="line2d_10">
+      <path d="M 97.2 445.429565
+L 1047.6 445.429565
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_11">
+      <defs>
+       <path id="m7e8e1ccff5" d="M 0 0
+L -3.5 0
+" style="stroke: #000000; stroke-width: 0.8"/>
+      </defs>
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="445.429565" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_11">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="449.988159" transform="rotate(-0 90.2 449.988159)">60</text>
+     </g>
+    </g>
+    <g id="ytick_2">
+     <g id="line2d_12">
+      <path d="M 97.2 389.551304
+L 1047.6 389.551304
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_13">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="389.551304" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_12">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="394.109898" transform="rotate(-0 90.2 394.109898)">65</text>
+     </g>
+    </g>
+    <g id="ytick_3">
+     <g id="line2d_14">
+      <path d="M 97.2 333.673043
+L 1047.6 333.673043
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_15">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="333.673043" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_13">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="338.231637" transform="rotate(-0 90.2 338.231637)">70</text>
+     </g>
+    </g>
+    <g id="ytick_4">
+     <g id="line2d_16">
+      <path d="M 97.2 277.794783
+L 1047.6 277.794783
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_17">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="277.794783" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_14">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="282.353376" transform="rotate(-0 90.2 282.353376)">75</text>
+     </g>
+    </g>
+    <g id="ytick_5">
+     <g id="line2d_18">
+      <path d="M 97.2 221.916522
+L 1047.6 221.916522
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_19">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="221.916522" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_15">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="226.475115" transform="rotate(-0 90.2 226.475115)">80</text>
+     </g>
+    </g>
+    <g id="ytick_6">
+     <g id="line2d_20">
+      <path d="M 97.2 166.038261
+L 1047.6 166.038261
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_21">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="166.038261" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_16">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="170.596855" transform="rotate(-0 90.2 170.596855)">85</text>
+     </g>
+    </g>
+    <g id="ytick_7">
+     <g id="line2d_22">
+      <path d="M 97.2 110.16
+L 1047.6 110.16
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke: #e7ebef; stroke-width: 0.8; stroke-linecap: square"/>
+     </g>
+     <g id="line2d_23">
+      <g>
+       <use xlink:href="#m7e8e1ccff5" x="97.2" y="110.16" style="stroke: #000000; stroke-width: 0.8"/>
+      </g>
+     </g>
+     <g id="text_17">
+      <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: end" x="90.2" y="114.718594" transform="rotate(-0 90.2 114.718594)">90</text>
+     </g>
+    </g>
+    <g id="text_18">
+     <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: middle" x="68.047188" y="302.94" transform="rotate(-90 68.047188 302.94)">Average Recall@5 (%)</text>
+    </g>
+   </g>
+   <g id="line2d_24">
+    <path d="M 123.198784 299.028522
+L 255.174996 221.497435
+L 304.195667 154.117565
+" clip-path="url(#pfb3f67a1a0)" style="fill: none; stroke-dasharray: 4.81,2.08; stroke-dashoffset: 0; stroke: #168568; stroke-opacity: 0.7; stroke-width: 1.3"/>
+   </g>
+   <g id="patch_3">
+    <path d="M 97.2 495.72
+L 97.2 110.16
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+   </g>
+   <g id="patch_4">
+    <path d="M 97.2 495.72
+L 1047.6 495.72
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+   </g>
+   <g id="text_19">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #777f8b" transform="translate(609.843161 216.153921)">HippoRAG 2</text>
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #777f8b" transform="translate(609.843161 232.522437)">82.55% · ≈8.25 s</text>
+   </g>
+   <g id="text_20">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #168568" transform="translate(265.174996 244.232747)">Jev · relations only</text>
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #168568" transform="translate(265.174996 260.601263)">80.04% · 2.28 s</text>
+   </g>
+   <g id="text_21">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #168568" transform="translate(314.195667 123.883581)">Jev · two-stage</text>
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #168568" transform="translate(314.195667 140.421393)">86.07% · 3.13 s</text>
+   </g>
+   <g id="text_22">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #a16826" transform="translate(442.363178 215.399524)">GPT-6 Luna</text>
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #a16826" transform="translate(442.363178 230.799524)">82.70% · 5.35 s</text>
+   </g>
+   <g id="text_23">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #2674bd" transform="translate(766.993357 154.553095)">DeepSeek V4.1 Flash</text>
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; fill: #2674bd" transform="translate(766.993357 170.921611)">83.34% · 10.97 s</text>
+   </g>
+   <g id="text_24">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #777f8b" x="135.198784" y="303.028522" transform="rotate(-0 135.198784 303.028522)">Naive RAG · NV-Embed-v2  (73.10%)</text>
+   </g>
+   <g id="text_25">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #777f8b" x="135.198784" y="389.31387" transform="rotate(-0 135.198784 389.31387)">Naive RAG · BGE-large-en-v1.5  (65.38%)</text>
+   </g>
+   <g id="text_26">
+    <text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #777f8b" x="135.198784" y="463.957913" transform="rotate(-0 135.198784 463.957913)">Naive RAG · ColBERTv2  (58.70%)</text>
+   </g>
+   <g id="PathCollection_1">
+    <defs>
+     <path id="m767e650826" d="M -4.472136 4.472136
+L 4.472136 4.472136
+L 4.472136 -4.472136
+L -4.472136 -4.472136
+z
+" style="stroke: #ffffff; stroke-width: 0.9"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m767e650826" x="599.843161" y="193.418609" style="fill: #777f8b; stroke: #ffffff; stroke-width: 0.9"/>
+    </g>
+   </g>
+   <g id="PathCollection_2">
+    <defs>
+     <path id="mdcc981d774" d="M 0 4.472136
+C 1.186024 4.472136 2.323632 4.000923 3.162278 3.162278
+C 4.000923 2.323632 4.472136 1.186024 4.472136 0
+C 4.472136 -1.186024 4.000923 -2.323632 3.162278 -3.162278
+C 2.323632 -4.000923 1.186024 -4.472136 0 -4.472136
+C -1.186024 -4.472136 -2.323632 -4.000923 -3.162278 -3.162278
+C -4.000923 -2.323632 -4.472136 -1.186024 -4.472136 0
+C -4.472136 1.186024 -4.000923 2.323632 -3.162278 3.162278
+C -2.323632 4.000923 -1.186024 4.472136 0 4.472136
+z
+" style="stroke: #ffffff; stroke-width: 0.9"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#mdcc981d774" x="255.174996" y="221.497435" style="fill: #168568; stroke: #ffffff; stroke-width: 0.9"/>
+    </g>
+   </g>
+   <g id="PathCollection_3">
+    <defs>
+     <path id="mfa49a455e4" d="M 0 -6.892024
+L -1.547356 -2.129753
+L -6.554705 -2.129753
+L -2.503674 0.813493
+L -4.05103 5.575765
+L -0 2.632519
+L 4.05103 5.575765
+L 2.503674 0.813493
+L 6.554705 -2.129753
+L 1.547356 -2.129753
+z
+" style="stroke: #ffffff; stroke-width: 0.9"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#mfa49a455e4" x="304.195667" y="154.117565" style="fill: #168568; stroke: #ffffff; stroke-width: 0.9"/>
+    </g>
+   </g>
+   <g id="PathCollection_4">
+    <defs>
+     <path id="m23881a4830" d="M 0 4.472136
+C 1.186024 4.472136 2.323632 4.000923 3.162278 3.162278
+C 4.000923 2.323632 4.472136 1.186024 4.472136 0
+C 4.472136 -1.186024 4.000923 -2.323632 3.162278 -3.162278
+C 2.323632 -4.000923 1.186024 -4.472136 0 -4.472136
+C -1.186024 -4.472136 -2.323632 -4.000923 -3.162278 -3.162278
+C -4.000923 -2.323632 -4.472136 -1.186024 -4.472136 0
+C -4.472136 1.186024 -4.000923 2.323632 -3.162278 3.162278
+C -2.323632 4.000923 -1.186024 4.472136 0 4.472136
+z
+" style="stroke: #ffffff; stroke-width: 0.9"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m23881a4830" x="432.363178" y="191.695696" style="fill: #a16826; stroke: #ffffff; stroke-width: 0.9"/>
+    </g>
+   </g>
+   <g id="PathCollection_5">
+    <defs>
+     <path id="m4d7c55c37c" d="M 0 4.472136
+C 1.186024 4.472136 2.323632 4.000923 3.162278 3.162278
+C 4.000923 2.323632 4.472136 1.186024 4.472136 0
+C 4.472136 -1.186024 4.000923 -2.323632 3.162278 -3.162278
+C 2.323632 -4.000923 1.186024 -4.472136 0 -4.472136
+C -1.186024 -4.472136 -2.323632 -4.000923 -3.162278 -3.162278
+C -4.000923 -2.323632 -4.472136 -1.186024 -4.472136 0
+C -4.472136 1.186024 -4.000923 2.323632 -3.162278 3.162278
+C -2.323632 4.000923 -1.186024 4.472136 0 4.472136
+z
+" style="stroke: #ffffff; stroke-width: 0.9"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m4d7c55c37c" x="756.993357" y="184.617783" style="fill: #2674bd; stroke: #ffffff; stroke-width: 0.9"/>
+    </g>
+   </g>
+   <g id="PathCollection_6">
+    <defs>
+     <path id="m077a5d3511" d="M -3.708099 3.708099
+L 3.708099 3.708099
+L 3.708099 -3.708099
+L -3.708099 -3.708099
+z
+" style="stroke: #777f8b"/>
+    </defs>
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m077a5d3511" x="123.198784" y="299.028522" style="fill: #ffffff; stroke: #777f8b"/>
+    </g>
+   </g>
+   <g id="PathCollection_7">
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m077a5d3511" x="123.198784" y="385.31387" style="fill: #ffffff; stroke: #777f8b"/>
+    </g>
+   </g>
+   <g id="PathCollection_8">
+    <g clip-path="url(#pfb3f67a1a0)">
+     <use xlink:href="#m077a5d3511" x="123.198784" y="459.957913" style="fill: #ffffff; stroke: #777f8b"/>
+    </g>
+   </g>
+   <g id="legend_1">
+    <g id="line2d_25">
+     <path d="M 855.489375 477.837187
+L 867.489375 477.837187
+L 879.489375 477.837187
+" style="fill: none; stroke-dasharray: 4.81,2.08; stroke-dashoffset: 0; stroke: #168568; stroke-opacity: 0.7; stroke-width: 1.3"/>
+    </g>
+    <g id="text_27">
+     <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: start" x="889.089375" y="482.037187" transform="rotate(-0 889.089375 482.037187)">Observed Pareto frontier</text>
+    </g>
+   </g>
+  </g>
+  <g id="text_28">
+   <text style="font-weight: 700; font-size: 22px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #253143" x="97.2" y="36.72" transform="rotate(-0 97.2 36.72)">Retrieval quality–latency trade-off</text>
+  </g>
+  <g id="text_29">
+   <text style="font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #657181" x="97.2" y="70.38" transform="rotate(-0 97.2 70.38)">MuSiQue + 2Wiki · Equal-weight Recall@5 · 1,000 queries per dataset</text>
+  </g>
+  <g id="text_30">
+   <text style="font-size: 10px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #657181" x="97.2" y="556.92" transform="rotate(-0 97.2 556.92)">Jev, Luna and Flash: measured API means. HippoRAG 2: reference estimate (≈); separate evaluation setup.</text>
+  </g>
+  <g id="text_31">
+   <text style="font-size: 10px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #657181" x="97.2" y="578.34" transform="rotate(-0 97.2 578.34)">0 s excludes embedding, retrieval and answer generation. API means include network and provider queueing; runs differ in time/concurrency.</text>
+  </g>
+ </g>
+ <defs>
+  <clipPath id="pfb3f67a1a0">
+   <rect x="97.2" y="110.16" width="950.4" height="385.56"/>
+  </clipPath>
+ </defs>
+</svg>