retrieval fusion

test-fusion.js

@@ -0,0 +1,67 @@
+// test-fusion.js
+const { RETRIEVAL } = require('./packages/shared/src/config/constants');
+
+function fuseEpisodeResults(semanticEps, keywordEps, { semanticWeight, keywordWeight, limit }) {
+    const k = RETRIEVAL.RRF_K;
+    const scores = new Map();
+    semanticEps.forEach((ep, i) => {
+        scores.set(ep.id, { episode: ep, score: semanticWeight / (k + i + 1) });
+    });
+    keywordEps.forEach((ep, i) => {
+        const contrib = keywordWeight / (k + i + 1);
+        if (scores.has(ep.id)) {
+            scores.get(ep.id).score += contrib;
+        } else {
+            scores.set(ep.id, { episode: ep, score: contrib });
+        }
+    });
+    return [...scores.values()]
+        .sort((a, b) => b.score - a.score)
+        .slice(0, limit)
+        .map(({ episode }) => episode);
+}
+
+// --- Test 1: episodes in both lists rank highest ---
+const semantic = [
+    { id: 1, user_message: 'ep1 — semantic only, rank 1' },
+    { id: 2, user_message: 'ep2 — in both lists, rank 2 semantic' },
+    { id: 3, user_message: 'ep3 — in both lists, rank 3 semantic' },
+];
+const keyword = [
+    { id: 3, user_message: 'ep3 — rank 1 FTS' },
+    { id: 2, user_message: 'ep2 — rank 2 FTS' },
+    { id: 4, user_message: 'ep4 — FTS only, rank 3' },
+];
+
+const result = fuseEpisodeResults(semantic, keyword, { semanticWeight: 1, keywordWeight: 1, limit: 5 });
+console.log('Test 1 — equal weights, episodes in both lists should rank highest:');
+result.forEach((ep, i) => console.log(`  ${i + 1}. id=${ep.id} "${ep.user_message}"`));
+console.assert(result[0].id === 2 || result[0].id === 3, 'FAIL: ep2 or ep3 should be rank 1');
+console.assert(!result.find(e => e.id === 1) || result.indexOf(result.find(e => e.id === 1)) > result.indexOf(result.find(e => e.id === 2)), 'FAIL: ep1 (semantic only) should rank below ep2');
+console.log('  PASS\n');
+
+// --- Test 2: keywordWeight:0 → pure semantic passthrough ---
+const result2 = fuseEpisodeResults(semantic, keyword, { semanticWeight: 1, keywordWeight: 0, limit: 5 });
+console.log('Test 2 — keywordWeight:0 should return only semantic results in original order:');
+result2.forEach((ep, i) => console.log(`  ${i + 1}. id=${ep.id}`));
+console.assert(result2.length === 3, `FAIL: expected 3, got ${result2.length}`);
+console.assert(result2[0].id === 1, 'FAIL: ep1 should be rank 1');
+console.assert(result2[1].id === 2, 'FAIL: ep2 should be rank 2');
+console.log('  PASS\n');
+
+// --- Test 3: limit is respected ---
+const result3 = fuseEpisodeResults(semantic, keyword, { semanticWeight: 1, keywordWeight: 1, limit: 2 });
+console.log('Test 3 — limit:2 should return exactly 2 results:');
+console.assert(result3.length === 2, `FAIL: expected 2, got ${result3.length}`);
+console.log('  PASS\n');
+
+// --- Test 4: no overlap → all unique episodes, ordered by individual contribution ---
+const semOnly = [{ id: 10, user_message: 'sem' }];
+const ftsOnly = [{ id: 20, user_message: 'fts' }];
+const result4 = fuseEpisodeResults(semOnly, ftsOnly, { semanticWeight: 1, keywordWeight: 1, limit: 5 });
+console.log('Test 4 — no overlap, both should appear:');
+console.assert(result4.length === 2, `FAIL: expected 2, got ${result4.length}`);
+console.assert(result4[0].id === 10, 'FAIL: semantic rank-1 should beat fts rank-1 (same weight, both rank 1, but semantic inserted first — tie goes to semantic)');
+console.log('  PASS\n');
+
+console.log('All tests passed.');