docarray · JoanFM · Jun 1, 2023 · May 31, 2023 · Jun 1, 2023 · Jun 1, 2023
diff --git a/docarray/index/backends/hnswlib.py b/docarray/index/backends/hnswlib.py
@@ -439,7 +439,7 @@ def _create_docs_table(self):
     def _send_docs_to_sqlite(self, docs: Sequence[BaseDoc]):
         ids = (self._to_hashed_id(doc.id) for doc in docs)
         self._sqlite_cursor.executemany(
-            'INSERT INTO docs VALUES (?, ?)',
+            'INSERT OR REPLACE INTO docs VALUES (?, ?)',
             ((id_, self._doc_to_bytes(doc)) for id_, doc in zip(ids, docs)),
         )
 

diff --git a/docs/user_guide/storing/index_hnswlib.md b/docs/user_guide/storing/index_hnswlib.md
@@ -208,4 +208,56 @@ To delete nested data, you need to specify the `id`.
 del doc_index[index_docs[6].id]
 ```
 
-Check [here](docindex#nested-data-with-subindex) for nested data with subindex.
+Check [here](../docindex#nested-data-with-subindex) for nested data with subindex.
+
+### Update elements
+In order to update a Document inside the index, you only need to reindex it with the updated attributes.
+
+First lets create a schema for our Index
+```python
+import numpy as np
+from docarray import BaseDoc, DocList
+from docarray.typing import NdArray
+from docarray.index import HnswDocumentIndex
+class MyDoc(BaseDoc):
+    text: str
+    embedding: NdArray[128]
+```
+Now we can instantiate our Index and index some data.
+
+```python
+docs = DocList[MyDoc](
+    [MyDoc(embedding=np.random.rand(10), text=f'I am the first version of Document {i}') for i in range(100)]
+)
+index = HnswDocumentIndex[MyDoc]()
+index.index(docs)
+assert index.num_docs() == 100
+```
+
+Now we can find relevant documents
+
+```python
+res = index.find(query=docs[0], search_field='tens', limit=100)
+assert len(res.documents) == 100
+for doc in res.documents:
+    assert 'I am the first version' in doc.text
+```
+
+and update all of the text of this documents and reindex them
+
+```python
+for i, doc in enumerate(docs):
+    doc.text = f'I am the second version of Document {i}'
+
+index.index(docs)
+assert index.num_docs() == 100
+```
+
+When we retrieve them again we can see that their text attribute has been updated accordingly
+
+```python
+res = index.find(query=docs[0], search_field='tens', limit=100)
+assert len(res.documents) == 100
+for doc in res.documents:
+    assert 'I am the second version' in doc.text
+```
diff --git a/tests/index/hnswlib/test_index_get_del.py b/tests/index/hnswlib/test_index_get_del.py
@@ -362,3 +362,53 @@ def test_num_docs(ten_simple_docs, tmp_path):
 
     del index[more_docs[2].id, ten_simple_docs[7].id]
     assert index.num_docs() == 10
+
+
+def test_update_payload(tmp_path):
+    class TextSimpleDoc(SimpleDoc):
+        text: str = 'hey'
+
+    docs = DocList[TextSimpleDoc](
+        [TextSimpleDoc(tens=np.random.rand(10), text=f'hey {i}') for i in range(100)]
+    )
+    index = HnswDocumentIndex[TextSimpleDoc](work_dir=str(tmp_path))
+    index.index(docs)
+    assert index.num_docs() == 100
+
+    for doc in docs:
+        doc.text += '_changed'
+
+    index.index(docs)
+    assert index.num_docs() == 100
+
+    res = index.find(query=docs[0], search_field='tens', limit=100)
+    assert len(res.documents) == 100
+    for doc in res.documents:
+        assert '_changed' in doc.text
+
+
+def test_update_embedding(tmp_path):
+    class TextSimpleDoc(SimpleDoc):
+        text: str = 'hey'
+
+    docs = DocList[TextSimpleDoc](
+        [TextSimpleDoc(tens=np.random.rand(10), text=f'hey {i}') for i in range(100)]
+    )
+    index = HnswDocumentIndex[TextSimpleDoc](work_dir=str(tmp_path))
+    index.index(docs)
+    assert index.num_docs() == 100
+
+    new_tensor = np.random.rand(10)
+    docs[0].tens = new_tensor
+
+    index.index(docs[0])
+    assert index.num_docs() == 100
+
+    res = index.find(query=docs[0], search_field='tens', limit=100)
+    assert len(res.documents) == 100
+    found = False
+    for doc in res.documents:
+        if doc.id == docs[0].id:
+            found = True
+            assert (doc.tens == new_tensor).all()
+    assert found