Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

fix(vector_stores/s3_vectors): make search score metric-aware (#6547)

Yash Singha2d8a8a84981
diff --git a/mem0/vector_stores/s3_vectors.py b/mem0/vector_stores/s3_vectors.py
index da059a409..55dadb878 100644
--- a/mem0/vector_stores/s3_vectors.py
+++ b/mem0/vector_stores/s3_vectors.py
@@ -69,6 +69,16 @@ class S3Vectors(VectorStoreBase):
else:
raise
+ def _distance_to_score(self, raw_distance: Optional[float]) -> Optional[float]:
+ if raw_distance is None:
+ return None
+ # Euclidean distance is unbounded, so 1 - distance would collapse most
+ # scores to 0. Use a bounded monotonic map instead. Cosine distance is
+ # in [0, 2], where 1 - distance is already a valid similarity.
+ if self.distance_metric == "euclidean":
+ return 1.0 / (1.0 + raw_distance)
+ return max(0.0, 1.0 - raw_distance)
+
def _parse_output(self, vectors: List[Dict]) -> List[OutputData]:
results = []
for v in vectors:
@@ -81,7 +91,7 @@ class S3Vectors(VectorStoreBase):
logger.warning(f"Failed to parse metadata for key {v.get('key')}")
payload = {}
raw_distance = v.get("distance")
- score = max(0.0, 1.0 - raw_distance) if raw_distance is not None else None
+ score = self._distance_to_score(raw_distance)
results.append(OutputData(id=v.get("key"), score=score, payload=payload))
return results
diff --git a/tests/vector_stores/test_s3_vectors.py b/tests/vector_stores/test_s3_vectors.py
index 68b7fa0f6..b72db32f4 100644
--- a/tests/vector_stores/test_s3_vectors.py
+++ b/tests/vector_stores/test_s3_vectors.py
@@ -186,6 +186,45 @@ def test_search(mock_boto_client):
assert results[0].score == pytest.approx(0.1)
+def test_search_score_cosine_uses_one_minus_distance(mock_boto_client):
+ """Cosine metric keeps the 1 - distance similarity mapping."""
+ mock_boto_client.query_vectors.return_value = {"vectors": [{"key": "id1", "distance": 0.25, "metadata": {}}]}
+ store = S3Vectors(
+ vector_bucket_name=BUCKET_NAME,
+ collection_name=INDEX_NAME,
+ embedding_model_dims=EMBEDDING_DIMS,
+ distance_metric="cosine",
+ )
+
+ results = store.search(query="test", vectors=[0.1, 0.2], top_k=1)
+
+ assert results[0].score == pytest.approx(0.75)
+
+
+def test_search_score_euclidean_uses_bounded_map(mock_boto_client):
+ """Euclidean distance is unbounded; scores must not collapse to 0."""
+ mock_boto_client.query_vectors.return_value = {
+ "vectors": [
+ {"key": "near", "distance": 0.5, "metadata": {}},
+ {"key": "far", "distance": 4.0, "metadata": {}},
+ ]
+ }
+ store = S3Vectors(
+ vector_bucket_name=BUCKET_NAME,
+ collection_name=INDEX_NAME,
+ embedding_model_dims=EMBEDDING_DIMS,
+ distance_metric="euclidean",
+ )
+
+ results = store.search(query="test", vectors=[0.1, 0.2], top_k=2)
+
+ # 1 / (1 + d): a distance > 1 would give a negative (clamped 0) score under
+ # the old cosine-only formula; the bounded map keeps ranking intact.
+ assert results[0].score == pytest.approx(1.0 / 1.5)
+ assert results[1].score == pytest.approx(1.0 / 5.0)
+ assert results[0].score > results[1].score > 0.0
+
+
def test_get(mock_boto_client):
"""Test retrieving a vector by ID."""
mock_boto_client.get_vectors.return_value = {