Add update_document_meta to InMemoryDocumentStore (deepset-ai#2689)

* Add update_document_meta to InMemoryDocumentStore

* Fix typo

* Update Documentation & Code Style

* Add update_document_meta to BaseDocumentStore

* Update Documentation & Code Style

* Fix mypy

* Update Documentation & Code Style

* Add update_document_meta to MockDocumentStore

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

docs/_src/api/api/document_store.md

@@ -669,7 +669,7 @@ Check out https://www.elastic.co/guide/en/elasticsearch/reference/current/http-c
 #### BaseElasticsearchDocumentStore.update\_document\_meta
 
 ```python
-def update_document_meta(id: str, meta: Dict[str, str], headers: Optional[Dict[str, str]] = None, index: str = None)
+def update_document_meta(id: str, meta: Dict[str, str], index: str = None, headers: Optional[Dict[str, str]] = None)
 ```
 
 Update the metadata dictionary of a document by specifying its string id
@@ -1907,6 +1907,22 @@ def get_document_count(filters: Optional[Dict[str, Any]] = None, index: Optional
 
 Return the number of documents in the document store.
 
+<a id="memory.InMemoryDocumentStore.update_document_meta"></a>
+
+#### InMemoryDocumentStore.update\_document\_meta
+
+```python
+def update_document_meta(id: str, meta: Dict[str, Any], index: str = None)
+```
+
+Update the metadata dictionary of a document by specifying its string id.
+
+**Arguments**:
+
+- `id`: The ID of the Document whose metadata is being updated.
+- `meta`: A dictionary with key-value pairs that should be added / changed for the provided Document ID.
+- `index`: Name of the index the Document is located at.
+
 <a id="memory.InMemoryDocumentStore.get_embedding_count"></a>
 
 #### InMemoryDocumentStore.get\_embedding\_count
@@ -4590,6 +4606,23 @@ exists.
 
 None
 
+<a id="deepsetcloud.DeepsetCloudDocumentStore.update_document_meta"></a>
+
+#### DeepsetCloudDocumentStore.update\_document\_meta
+
+```python
+@disable_and_log
+def update_document_meta(id: str, meta: Dict[str, Any], index: str = None)
+```
+
+Update the metadata dictionary of a document by specifying its string id.
+
+**Arguments**:
+
+- `id`: The ID of the Document whose metadata is being updated.
+- `meta`: A dictionary with key-value pairs that should be added / changed for the provided Document ID.
+- `index`: Name of the index the Document is located at.
+
 <a id="deepsetcloud.DeepsetCloudDocumentStore.get_evaluation_sets"></a>
 
 #### DeepsetCloudDocumentStore.get\_evaluation\_sets

haystack/document_stores/base.py

@@ -1,6 +1,6 @@
 # pylint: disable=too-many-public-methods
 
-from typing import Generator, Optional, Dict, List, Set, Union
+from typing import Generator, Optional, Dict, List, Set, Union, Any
 
 import logging
 import collections
@@ -607,6 +607,10 @@ def get_documents_by_id(
     ) -> List[Document]:
         pass
 
+    @abstractmethod
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+        pass
+
     def _drop_duplicate_documents(self, documents: List[Document], index: Optional[str] = None) -> List[Document]:
         """
         Drop duplicates documents based on same hash ID

haystack/document_stores/deepsetcloud.py

@@ -1,5 +1,5 @@
 from functools import wraps
-from typing import List, Optional, Union, Dict, Generator
+from typing import List, Optional, Union, Dict, Generator, Any
 
 import json
 import logging
@@ -602,6 +602,17 @@ def write_documents(
         """
         pass
 
+    @disable_and_log
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+        """
+        Update the metadata dictionary of a document by specifying its string id.
+
+        :param id: The ID of the Document whose metadata is being updated.
+        :param meta: A dictionary with key-value pairs that should be added / changed for the provided Document ID.
+        :param index: Name of the index the Document is located at.
+        """
+        pass
+
     def get_evaluation_sets(self) -> List[dict]:
         """
         Returns a list of uploaded evaluation sets to deepset cloud.

haystack/document_stores/elasticsearch.py

@@ -506,7 +506,7 @@ def write_labels(
             bulk(self.client, labels_to_index, request_timeout=300, refresh=self.refresh_type, headers=headers)
 
     def update_document_meta(
-        self, id: str, meta: Dict[str, str], headers: Optional[Dict[str, str]] = None, index: str = None
+        self, id: str, meta: Dict[str, str], index: str = None, headers: Optional[Dict[str, str]] = None
     ):
         """
         Update the metadata dictionary of a document by specifying its string id

haystack/document_stores/memory.py

@@ -480,6 +480,19 @@ def get_document_count(
         )
         return len(documents)
 
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+        """
+        Update the metadata dictionary of a document by specifying its string id.
+
+        :param id: The ID of the Document whose metadata is being updated.
+        :param meta: A dictionary with key-value pairs that should be added / changed for the provided Document ID.
+        :param index: Name of the index the Document is located at.
+        """
+        if index is None:
+            index = self.index
+        for key, value in meta.items():
+            self.indexes[index][id].meta[key] = value
+
     def get_embedding_count(self, filters: Optional[Dict[str, List[str]]] = None, index: Optional[str] = None) -> int:
         """
         Return the count of embeddings in the document store.

test/conftest.py

@@ -227,6 +227,9 @@ def write_labels(self, *a, **k):
     def delete_index(self, *a, **k):
         pass
 
+    def update_document_meta(self, *a, **kw):
+        pass
+
 
 class MockRetriever(BaseRetriever):
     outgoing_edges = 1

test/document_stores/test_document_store.py

@@ -1185,8 +1185,9 @@ def test_multilabel_meta_aggregations(document_store: BaseDocumentStore):
             assert multi_label.filters == l.filters
 
 
-@pytest.mark.parametrize("document_store", ["elasticsearch", "faiss", "milvus1", "weaviate", "pinecone"], indirect=True)
-# Currently update_document_meta() is not implemented for Memory doc store
+@pytest.mark.parametrize(
+    "document_store", ["elasticsearch", "faiss", "milvus1", "weaviate", "pinecone", "memory"], indirect=True
+)
 def test_update_meta(document_store: BaseDocumentStore):
     documents = [
         Document(content="Doc1", meta={"meta_key_1": "1", "meta_key_2": "1"}),