fix(memory): align entity extraction precision (#5829)

Making the entity extraction function cleaner


Co-authored-by: Soumil Rathi <soumilrathi@gmail.com>

tests/utils/test_entity_extraction.py

@@ -6,6 +6,7 @@ def _ensure_spacy():
     """Skip tests if spaCy model is not available."""
     try:
         import spacy
+
         spacy.load("en_core_web_sm")
     except Exception:
         pytest.skip("spaCy en_core_web_sm model not available")
@@ -33,8 +34,9 @@ class TestExtractEntities:
 
         entities = extract_entities("The machine learning engineer built a neural network")
         entity_texts = [e[1].lower() for e in entities]
-        has_compound = any("machine" in t and "learning" in t for t in entity_texts) or \
-                       any("neural" in t and "network" in t for t in entity_texts)
+        has_compound = any("machine" in t and "learning" in t for t in entity_texts) or any(
+            "neural" in t and "network" in t for t in entity_texts
+        )
         assert has_compound, f"Expected compound nouns, got {entities}"
 
     def test_empty_string(self):
@@ -76,9 +78,37 @@ class TestExtractEntities:
         for entity in entities:
             assert isinstance(entity, tuple)
             assert len(entity) == 2
-            assert entity[0] in ("PROPER", "QUOTED", "COMPOUND", "NOUN")
+            assert entity[0] in ("PROPER", "QUOTED", "TOPIC", "IDENTIFIER")
             assert isinstance(entity[1], str)
 
+    def test_handles_names_lists_and_identifiers(self):
+        from mem0.utils.entity_extraction import extract_entities
+
+        text = (
+            "User reported top inbound integration pages: OpenClaw 25,443, "
+            "Claude Code 8,916, Codex 2,573, Dify 656. "
+            "User compared Cartesia and Deepgram. "
+            "The email field for Mem0 lives at person.properties.email. "
+            "The qwen endpoint uses person.properties.email. "
+            "Johnson & Johnson was mentioned. "
+            "Glasses around my window. "
+            "On 2026-05-27 there were 90 days of stats."
+        )
+
+        entities = extract_entities(text)
+        entity_texts = {entity_text for _, entity_text in entities}
+        normalized = {entity_text.lower() for entity_text in entity_texts}
+
+        assert {"OpenClaw", "Claude Code", "Codex", "Dify", "Cartesia", "Deepgram", "Mem0"}.issubset(entity_texts)
+        assert "person.properties.email" in entity_texts
+        assert "qwen endpoint" in entity_texts
+        assert "Johnson & Johnson" in entity_texts
+        assert "top" not in normalized
+        assert "glasses" not in normalized
+        assert "Cartesia and Deepgram" not in entity_texts
+        assert "Claude Code 8,916" not in entity_texts
+        assert not {"8,916", "2,573", "656", "2026-05-27", "90"}.intersection(entity_texts)
+
 
 class TestExtractEntitiesBatch:
     def test_batch_processing(self):