fix: normalize vector store scores to similarity (higher = better)

The threshold parameter in Memory.search() was silently broken for 11
vector stores because they returned raw distance scores (lower = better)
while the threshold check assumed similarity scores (higher = better).
This caused threshold filtering to be inverted — good matches got
dropped and bad matches passed through.

Convert all affected vector stores to return similarity scores:
- Cosine distance stores: score = max(0.0, 1.0 - distance)
- L2 distance stores: score = 1.0 / (1.0 + distance)
- Stores computing similarity then discarding it: return similarity directly

Fixes #4453
Related: #3283

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
utkarsh240799
2026-03-28 21:57:40 +05:30
co-authored by Claude Opus 4.6
parent 431cba20e9
commit 224fd6c7d8
18 changed files with 79 additions and 48 deletions
+12 -12
View File
@@ -445,9 +445,9 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 2)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[1].id, self.test_ids[1])
self.assertEqual(results[1].score, 0.2)
self.assertEqual(results[1].score, 0.8)
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 2)
@patch('mem0.vector_stores.pgvector.ConnectionPool')
@@ -494,9 +494,9 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 2)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[1].id, self.test_ids[1])
self.assertEqual(results[1].score, 0.2)
self.assertEqual(results[1].score, 0.8)
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 3)
@patch('mem0.vector_stores.pgvector.ConnectionPool')
@@ -1140,7 +1140,7 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 1)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[0].payload["user_id"], "alice")
self.assertEqual(results[0].payload["agent_id"], "agent1")
self.assertEqual(results[0].payload["run_id"], "run1")
@@ -1190,7 +1190,7 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 1)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[0].payload["user_id"], "alice")
self.assertEqual(results[0].payload["agent_id"], "agent1")
self.assertEqual(results[0].payload["run_id"], "run1")
@@ -1240,7 +1240,7 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 1)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[0].payload["user_id"], "alice")
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 2)
@@ -1288,7 +1288,7 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 1)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[0].payload["user_id"], "alice")
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 3)
@@ -1336,9 +1336,9 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 2)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[1].id, self.test_ids[1])
self.assertEqual(results[1].score, 0.2)
self.assertEqual(results[1].score, 0.8)
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 2)
@patch('mem0.vector_stores.pgvector.ConnectionPool')
@@ -1385,9 +1385,9 @@ class TestPGVector(unittest.TestCase):
# Verify results
self.assertEqual(len(results), 2)
self.assertEqual(results[0].id, self.test_ids[0])
self.assertEqual(results[0].score, 0.1)
self.assertEqual(results[0].score, 0.9)
self.assertEqual(results[1].id, self.test_ids[1])
self.assertEqual(results[1].score, 0.2)
self.assertEqual(results[1].score, 0.8)
@patch('mem0.vector_stores.pgvector.PSYCOPG_VERSION', 3)
@patch('mem0.vector_stores.pgvector.ConnectionPool')