fix(checkpoint): preserve non-ascii text in InMemoryStore embeddings (#6111)

### Description
* Set `ensure_ascii=False` for all `json.dumps` calls in
`get_text_at_path`. Preserves non-ASCII text instead of embedding
`\uXXXX` escapes.

**Before**
```python
store.put(("user_123", "memories"), "1", {"text": "这是中文"})
# embeds {"text": "\\u8fd9\\u662f\\u4e2d\\u6587"}
```

**After**
```python
store.put(("user_123", "memories"), "1", {"text": "这是中文"})
# embeds {"text": "这是中文"}
```

### Tests & Docs

* Add unit test `test_non_ascii` that writes three records (Chinese,
Japanese, Korean) to an `InMemoryStore`, searches with the same strings,
and asserts the correct top hit with a score >= 0.15 for each.

### Issue
Fixes #5946
This commit is contained in:
Caspar Broekhuizen
2025-09-09 17:52:11 +00:00
committed by GitHub
parent 7bbe8d8628
commit 682f39e0d3
5 changed files with 151 additions and 45 deletions
@@ -1067,3 +1067,31 @@ def test_sql_injection_vulnerability(store: SqliteStore) -> None:
with pytest.raises(ValueError, match="Invalid filter key"):
store.search(("docs",), filter={malicious_key: "dummy"})
@pytest.mark.parametrize("distance_type", VECTOR_TYPES)
def test_non_ascii(
fake_embeddings: CharacterEmbeddings,
distance_type: str,
) -> None:
"""Test support for non-ascii characters"""
with create_vector_store(fake_embeddings, distance_type=distance_type) as store:
store.put(("user_123", "memories"), "1", {"text": "这是中文"}) # Chinese
store.put(
("user_123", "memories"), "2", {"text": "これは日本語です"}
) # Japanese
store.put(("user_123", "memories"), "3", {"text": "이건 한국어야"}) # Korean
store.put(("user_123", "memories"), "4", {"text": "Это русский"}) # Russian
store.put(("user_123", "memories"), "5", {"text": "यह रूसी है"}) # Hindi
result1 = store.search(("user_123", "memories"), query="这是中文")
result2 = store.search(("user_123", "memories"), query="これは日本語です")
result3 = store.search(("user_123", "memories"), query="이건 한국어야")
result4 = store.search(("user_123", "memories"), query="Это русский")
result5 = store.search(("user_123", "memories"), query="यह रूसी है")
assert result1[0].key == "1"
assert result2[0].key == "2"
assert result3[0].key == "3"
assert result4[0].key == "4"
assert result5[0].key == "5"