add config files loading and display

package-lock.json

@@ -9,11 +9,13 @@
       "version": "0.0.0",
       "dependencies": {
         "@huggingface/hub": "^2.7.1",
+        "js-yaml": "^4.1.1",
         "marked": "^17.0.1"
       },
       "devDependencies": {
         "@sveltejs/vite-plugin-svelte": "^5.0.3",
         "@tsconfig/svelte": "^5.0.4",
+        "@types/js-yaml": "^4.0.9",
         "svelte": "^5.28.1",
         "svelte-check": "^4.1.6",
         "typescript": "~5.8.3",
@@ -908,6 +910,13 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/@types/js-yaml": {
+      "version": "4.0.9",
+      "resolved": "https://registry.npmjs.org/@types/js-yaml/-/js-yaml-4.0.9.tgz",
+      "integrity": "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/acorn": {
       "version": "8.15.0",
       "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
@@ -931,6 +940,12 @@
         "node": ">=8"
       }
     },
+    "node_modules/argparse": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/argparse/-/argparse-2.0.1.tgz",
+      "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q==",
+      "license": "Python-2.0"
+    },
     "node_modules/aria-query": {
       "version": "5.3.2",
       "resolved": "https://registry.npmjs.org/aria-query/-/aria-query-5.3.2.tgz",
@@ -1144,6 +1159,18 @@
         "@types/estree": "^1.0.6"
       }
     },
+    "node_modules/js-yaml": {
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.1.tgz",
+      "integrity": "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA==",
+      "license": "MIT",
+      "dependencies": {
+        "argparse": "^2.0.1"
+      },
+      "bin": {
+        "js-yaml": "bin/js-yaml.js"
+      }
+    },
     "node_modules/kleur": {
       "version": "4.1.5",
       "resolved": "https://registry.npmjs.org/kleur/-/kleur-4.1.5.tgz",

package.json

@@ -12,6 +12,7 @@
   "devDependencies": {
     "@sveltejs/vite-plugin-svelte": "^5.0.3",
     "@tsconfig/svelte": "^5.0.4",
+    "@types/js-yaml": "^4.0.9",
     "svelte": "^5.28.1",
     "svelte-check": "^4.1.6",
     "typescript": "~5.8.3",
@@ -19,6 +20,7 @@
   },
   "dependencies": {
     "@huggingface/hub": "^2.7.1",
+    "js-yaml": "^4.1.1",
     "marked": "^17.0.1"
   }
 }

src/lib/DatasetViewer.svelte

@@ -1,5 +1,9 @@
 <script lang="ts">
-  import { fetchAllRows } from "./huggingfaceApi";
+  import {
+    fetchAllRows,
+    fetchDatasetConfigYaml,
+    type DatasetConfigYaml,
+  } from "./huggingfaceApi";
   import type { TermDefinition, EquivalencyScore } from "./types";
   import { marked } from "marked";
   import { config, getDatasetName } from "./config";
@@ -28,6 +32,7 @@
   let equivalencyScores = $state<EquivalencyScore[]>([]);
   let selectedTerm1 = $state<string | null>(null);
   let selectedTerm2 = $state<string | null>(null);
+  let datasetConfig = $state<DatasetConfigYaml | null>(null);
 
   // Track previous selected terms for detecting user-initiated changes (loop prevention)
   let prevSelectedTerm1 = $state<string | null>(null);
@@ -98,6 +103,20 @@
 
       hasLoaded = true;
 
+      // Fetch config.yaml for this jurisdiction pair
+      try {
+        const configPath = `${jurisdiction1}_${jurisdiction2}/config.yaml`;
+        datasetConfig = await fetchDatasetConfigYaml(
+          scoresDataset,
+          configPath,
+          "main",
+          undefined
+        );
+      } catch (e) {
+        datasetConfig = null;
+        console.warn("Could not load dataset config.yaml", e);
+      }
+
       // Auto-select first term from jurisdiction 1 and its equivalent in jurisdiction 2
       if (data1.length > 0) {
         const firstTerm = data1[0].term;
@@ -270,6 +289,22 @@
 <div class="jurisdiction-comparison">
   <h2>Jurisdiction Term Comparison</h2>
 
+  <!-- Model Info Display -->
+  {#if datasetConfig}
+    <div class="dataset-model-info subtle">
+      <span><strong>Scoring Model:</strong> {datasetConfig.scoring_model}</span>
+      <span class="sep">|</span>
+      <span
+        ><strong>Synthesis Model:</strong> {datasetConfig.synthesis_model}</span
+      >
+      <span class="sep">|</span>
+      <span
+        ><strong>Last Updated:</strong>
+        {datasetConfig.generation_date || "N/A"}</span
+      >
+    </div>
+  {/if}
+
   <div class="form">
     <div class="form-row">
       <div class="form-group">
@@ -981,4 +1016,29 @@
     background: #535bf2;
     border-color: #535bf2;
   }
+
+  .dataset-model-info.subtle {
+    background: none;
+    border: none;
+    padding: 0.25rem 0;
+    margin: 0 0 0.5rem 0;
+    max-width: 100%;
+    color: #888;
+    font-size: 0.92rem;
+    text-align: left;
+    display: flex;
+    flex-wrap: wrap;
+    gap: 0.5rem;
+    align-items: center;
+  }
+  .dataset-model-info.subtle strong {
+    color: #888;
+    font-weight: 500;
+    margin-right: 0.15em;
+  }
+  .dataset-model-info.subtle .sep {
+    color: #ccc;
+    font-size: 1.1em;
+    margin: 0 0.5em;
+  }
 </style>

src/lib/huggingfaceApi.ts

@@ -5,7 +5,7 @@ import type {
   DatasetSplitsResponse,
   DatasetError,
 } from "./types";
-
+import yaml from "js-yaml";
 const BASE_URL = "https://datasets-server.huggingface.co";
 
 /**
@@ -156,3 +156,45 @@ export async function fetchAllRows(
 
   return allRows;
 }
+
+export async function fetchDatasetFileRaw(
+  dataset: string, // "owner/dataset-name"
+  filePath: string, // "config.yaml"
+  branch = "main",
+  token?: string
+): Promise<string> {
+  const url = `https://huggingface.co/datasets/${dataset}/raw/${encodeURIComponent(
+    branch
+  )}/${filePath}`;
+  const headers: HeadersInit = {};
+  if (token) {
+    headers["Authorization"] = `Bearer ${token}`;
+  }
+  const res = await fetch(url, { headers });
+  if (!res.ok)
+    throw new Error(`Failed to fetch file: ${res.status} ${res.statusText}`);
+  return res.text();
+}
+
+export interface DatasetConfigYaml {
+  scoring_model: string;
+  scoring_provider: string;
+  synthesis_model: string;
+  synthesis_provider: string;
+  jurisdiction1: string;
+  jurisdiction2: string;
+  description: string;
+  grading_templates_1_uid: string;
+  grading_templates_2_uid: string;
+  generation_date?: string;
+}
+
+export async function fetchDatasetConfigYaml(
+  dataset: string,
+  filePath = "config.yaml",
+  branch = "main",
+  token?: string
+): Promise<DatasetConfigYaml | null> {
+  const text = await fetchDatasetFileRaw(dataset, filePath, branch, token);
+  return yaml.load(text) as DatasetConfigYaml;
+}