fix(rag/nlp): treat string input as one phrase in is_english (#16308)

rag/nlp/__init__.py

@@ -240,7 +240,7 @@ def is_english(texts):
     pattern = re.compile(r"[`a-zA-Z0-9\s.,':;/\"?<>!\(\)\-]+")
 
     if isinstance(texts, str):
-        texts = list(texts)
+        texts = [texts]
     elif isinstance(texts, list):
         texts = [t for t in texts if isinstance(t, str) and t.strip()]
     else:

test/unit_test/rag/test_is_english.py

@@ -55,6 +55,12 @@ def test_is_english_single_english_answer_in_list():
     assert is_english(["This is a normal English answer."]) is True
 
 
+@pytest.mark.p2
+def test_is_english_multi_word_phrase():
+    # Regression: splitting a string into characters made short spaced phrases fail.
+    assert is_english("I am good") is True
+
+
 @pytest.mark.p2
 def test_is_english_chinese_list_is_false():
     assert is_english(["这是中文段落。", "另一个中文段落。"]) is False