elasticsearch 9.1.0__py3-none-any.whl → 9.1.1__py3-none-any.whl

elasticsearch/_sync/client/cluster.py

@@ -374,8 +374,13 @@ class ClusterClient(NamespacedClient):
         `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-cluster-get-settings>`_
 
         :param flat_settings: If `true`, returns settings in flat format.
-        :param include_defaults: If `true`, returns default cluster settings from the
-            local node.
+        :param include_defaults: If `true`, also returns default values for all other
+            cluster settings, reflecting the values in the `elasticsearch.yml` file of
+            one of the nodes in the cluster. If the nodes in your cluster do not all
+            have the same values in their `elasticsearch.yml` config files then the values
+            returned by this API may vary from invocation to invocation and may not reflect
+            the values that Elasticsearch uses in all situations. Use the `GET _nodes/settings`
+            API to fetch the settings for each individual node in your cluster.
         :param master_timeout: Period to wait for a connection to the master node. If
             no response is received before the timeout expires, the request fails and
             returns an error.

elasticsearch/_sync/client/esql.py

@@ -28,6 +28,9 @@ from .utils import (
     _stability_warning,
 )
 
+if t.TYPE_CHECKING:
+    from elasticsearch.esql import ESQLBase
+
 
 class EsqlClient(NamespacedClient):
 
@@ -50,7 +53,7 @@ class EsqlClient(NamespacedClient):
     def async_query(
         self,
         *,
-        query: t.Optional[str] = None,
+        query: t.Optional[t.Union[str, "ESQLBase"]] = None,
         allow_partial_results: t.Optional[bool] = None,
         columnar: t.Optional[bool] = None,
         delimiter: t.Optional[str] = None,
@@ -111,7 +114,12 @@ class EsqlClient(NamespacedClient):
             which has the name of all the columns.
         :param filter: Specify a Query DSL query in the filter parameter to filter the
             set of documents that an ES|QL query runs on.
-        :param format: A short version of the Accept header, for example `json` or `yaml`.
+        :param format: A short version of the Accept header, e.g. json, yaml. `csv`,
+            `tsv`, and `txt` formats will return results in a tabular format, excluding
+            other metadata fields from the response. For async requests, nothing will
+            be returned if the async query doesn't finish within the timeout. The query
+            ID and running status are available in the `X-Elasticsearch-Async-Id` and
+            `X-Elasticsearch-Async-Is-Running` HTTP headers of the response, respectively.
         :param include_ccs_metadata: When set to `true` and performing a cross-cluster
             query, the response will include an extra `_clusters` object with information
             about the clusters that participated in the search along with info such as
@@ -165,7 +173,7 @@ class EsqlClient(NamespacedClient):
             __query["pretty"] = pretty
         if not __body:
             if query is not None:
-                __body["query"] = query
+                __body["query"] = str(query)
             if columnar is not None:
                 __body["columnar"] = columnar
             if filter is not None:
@@ -405,6 +413,8 @@ class EsqlClient(NamespacedClient):
           Returns an object extended information about a running ES|QL query.</p>
 
 
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-esql-get-query>`_
+
         :param id: The query ID
         """
         if id in SKIP_IN_PATH:
@@ -446,6 +456,8 @@ class EsqlClient(NamespacedClient):
           <p>Get running ES|QL queries information.
           Returns an object containing IDs and other information about the running ES|QL queries.</p>
 
+
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-esql-list-queries>`_
         """
         __path_parts: t.Dict[str, str] = {}
         __path = "/_query/queries"
@@ -484,7 +496,7 @@ class EsqlClient(NamespacedClient):
     def query(
         self,
         *,
-        query: t.Optional[str] = None,
+        query: t.Optional[t.Union[str, "ESQLBase"]] = None,
         allow_partial_results: t.Optional[bool] = None,
         columnar: t.Optional[bool] = None,
         delimiter: t.Optional[str] = None,
@@ -539,7 +551,9 @@ class EsqlClient(NamespacedClient):
             `all_columns` which has the name of all columns.
         :param filter: Specify a Query DSL query in the filter parameter to filter the
             set of documents that an ES|QL query runs on.
-        :param format: A short version of the Accept header, e.g. json, yaml.
+        :param format: A short version of the Accept header, e.g. json, yaml. `csv`,
+            `tsv`, and `txt` formats will return results in a tabular format, excluding
+            other metadata fields from the response.
         :param include_ccs_metadata: When set to `true` and performing a cross-cluster
             query, the response will include an extra `_clusters` object with information
             about the clusters that participated in the search along with info such as
@@ -579,7 +593,7 @@ class EsqlClient(NamespacedClient):
             __query["pretty"] = pretty
         if not __body:
             if query is not None:
-                __body["query"] = query
+                __body["query"] = str(query)
             if columnar is not None:
                 __body["columnar"] = columnar
             if filter is not None:

elasticsearch/_sync/client/indices.py

@@ -1208,7 +1208,7 @@ class IndicesClient(NamespacedClient):
           Removes the data stream options from a data stream.</p>
 
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/9.1/index.html>`_
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-delete-data-stream-options>`_
 
         :param name: A comma-separated list of data streams of which the data stream
             options will be deleted; use `*` to get all data streams
@@ -2568,7 +2568,7 @@ class IndicesClient(NamespacedClient):
           <p>Get the data stream options configuration of one or more data streams.</p>
 
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/9.1/index.html>`_
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-get-data-stream-options>`_
 
         :param name: Comma-separated list of data streams to limit the request. Supports
             wildcards (`*`). To target all data streams, omit this parameter or use `*`
@@ -3684,7 +3684,7 @@ class IndicesClient(NamespacedClient):
           Update the data stream options of the specified data streams.</p>
 
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/9.1/index.html>`_
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-put-data-stream-options>`_
 
         :param name: Comma-separated list of data streams used to limit the request.
             Supports wildcards (`*`). To target all data streams use `*` or `_all`.
@@ -4051,7 +4051,7 @@ class IndicesClient(NamespacedClient):
           <li>Change a field's mapping using reindexing</li>
           <li>Rename a field using a field alias</li>
           </ul>
-          <p>Learn how to use the update mapping API with practical examples in the <a href="https://www.elastic.co/docs//manage-data/data-store/mapping/update-mappings-examples">Update mapping API examples</a> guide.</p>
+          <p>Learn how to use the update mapping API with practical examples in the <a href="https://www.elastic.co/docs/manage-data/data-store/mapping/update-mappings-examples">Update mapping API examples</a> guide.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-indices-put-mapping>`_

elasticsearch/_sync/client/inference.py

@@ -396,17 +396,18 @@ class InferenceClient(NamespacedClient):
           <li>Azure AI Studio (<code>completion</code>, <code>text_embedding</code>)</li>
           <li>Azure OpenAI (<code>completion</code>, <code>text_embedding</code>)</li>
           <li>Cohere (<code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
-          <li>DeepSeek (<code>completion</code>, <code>chat_completion</code>)</li>
+          <li>DeepSeek (<code>chat_completion</code>, <code>completion</code>)</li>
           <li>Elasticsearch (<code>rerank</code>, <code>sparse_embedding</code>, <code>text_embedding</code> - this service is for built-in models and models uploaded through Eland)</li>
           <li>ELSER (<code>sparse_embedding</code>)</li>
           <li>Google AI Studio (<code>completion</code>, <code>text_embedding</code>)</li>
-          <li>Google Vertex AI (<code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>Google Vertex AI (<code>chat_completion</code>, <code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
           <li>Hugging Face (<code>chat_completion</code>, <code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>JinaAI (<code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>Llama (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
           <li>Mistral (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
           <li>OpenAI (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
-          <li>VoyageAI (<code>text_embedding</code>, <code>rerank</code>)</li>
+          <li>VoyageAI (<code>rerank</code>, <code>text_embedding</code>)</li>
           <li>Watsonx inference integration (<code>text_embedding</code>)</li>
-          <li>JinaAI (<code>text_embedding</code>, <code>rerank</code>)</li>
           </ul>
 
 

elasticsearch/_sync/client/sql.py

@@ -283,7 +283,7 @@ class SqlClient(NamespacedClient):
         keep_alive: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         keep_on_completion: t.Optional[bool] = None,
         page_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
-        params: t.Optional[t.Mapping[str, t.Any]] = None,
+        params: t.Optional[t.Sequence[t.Any]] = None,
         pretty: t.Optional[bool] = None,
         query: t.Optional[str] = None,
         request_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,

elasticsearch/_sync/client/transform.py

@@ -602,6 +602,66 @@ class TransformClient(NamespacedClient):
             path_parts=__path_parts,
         )
 
+    @_rewrite_parameters()
+    def set_upgrade_mode(
+        self,
+        *,
+        enabled: t.Optional[bool] = None,
+        error_trace: t.Optional[bool] = None,
+        filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        human: t.Optional[bool] = None,
+        pretty: t.Optional[bool] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
+    ) -> ObjectApiResponse[t.Any]:
+        """
+        .. raw:: html
+
+          <p>Set upgrade_mode for transform indices.
+          Sets a cluster wide upgrade_mode setting that prepares transform
+          indices for an upgrade.
+          When upgrading your cluster, in some circumstances you must restart your
+          nodes and reindex your transform indices. In those circumstances,
+          there must be no transforms running. You can close the transforms,
+          do the upgrade, then open all the transforms again. Alternatively,
+          you can use this API to temporarily halt tasks associated with the transforms
+          and prevent new transforms from opening. You can also use this API
+          during upgrades that do not require you to reindex your transform
+          indices, though stopping transforms is not a requirement in that case.
+          You can see the current value for the upgrade_mode setting by using the get
+          transform info API.</p>
+
+
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-transform-set-upgrade-mode>`_
+
+        :param enabled: When `true`, it enables `upgrade_mode` which temporarily halts
+            all transform tasks and prohibits new transform tasks from starting.
+        :param timeout: The time to wait for the request to be completed.
+        """
+        __path_parts: t.Dict[str, str] = {}
+        __path = "/_transform/set_upgrade_mode"
+        __query: t.Dict[str, t.Any] = {}
+        if enabled is not None:
+            __query["enabled"] = enabled
+        if error_trace is not None:
+            __query["error_trace"] = error_trace
+        if filter_path is not None:
+            __query["filter_path"] = filter_path
+        if human is not None:
+            __query["human"] = human
+        if pretty is not None:
+            __query["pretty"] = pretty
+        if timeout is not None:
+            __query["timeout"] = timeout
+        __headers = {"accept": "application/json"}
+        return self.perform_request(  # type: ignore[return-value]
+            "POST",
+            __path,
+            params=__query,
+            headers=__headers,
+            endpoint_id="transform.set_upgrade_mode",
+            path_parts=__path_parts,
+        )
+
     @_rewrite_parameters(
         parameter_aliases={"from": "from_"},
     )

elasticsearch/_version.py

@@ -15,4 +15,4 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
-__versionstr__ = "9.1.0"
+__versionstr__ = "9.1.1"

elasticsearch/dsl/_async/document.py

@@ -20,6 +20,7 @@ from typing import (
     TYPE_CHECKING,
     Any,
     AsyncIterable,
+    AsyncIterator,
     Dict,
     List,
     Optional,
@@ -42,6 +43,7 @@ from .search import AsyncSearch
 
 if TYPE_CHECKING:
     from elasticsearch import AsyncElasticsearch
+    from elasticsearch.esql.esql import ESQLBase
 
 
 class AsyncIndexMeta(DocumentMeta):
@@ -520,3 +522,85 @@ class AsyncDocument(DocumentBase, metaclass=AsyncIndexMeta):
                 return action
 
         return await async_bulk(es, Generate(actions), **kwargs)
+
+    @classmethod
+    async def esql_execute(
+        cls,
+        query: "ESQLBase",
+        return_additional: bool = False,
+        ignore_missing_fields: bool = False,
+        using: Optional[AsyncUsingType] = None,
+        **kwargs: Any,
+    ) -> AsyncIterator[Union[Self, Tuple[Self, Dict[str, Any]]]]:
+        """
+        Execute the given ES|QL query and return an iterator of 2-element tuples,
+        where the first element is an instance of this ``Document`` and the
+        second a dictionary with any remaining columns requested in the query.
+
+        :arg query: an ES|QL query object created with the ``esql_from()`` method.
+        :arg return_additional: if ``False`` (the default), this method returns
+            document objects. If set to ``True``, the method returns tuples with
+            a document in the first element and a dictionary with any additional
+            columns returned by the query in the second element.
+        :arg ignore_missing_fields: if ``False`` (the default), all the fields of
+            the document must be present in the query, or else an exception is
+            raised. Set to ``True`` to allow missing fields, which will result in
+            partially initialized document objects.
+        :arg using: connection alias to use, defaults to ``'default'``
+        :arg kwargs: additional options for the ``client.esql.query()`` function.
+        """
+        es = cls._get_connection(using)
+        response = await es.esql.query(query=str(query), **kwargs)
+        query_columns = [col["name"] for col in response.body.get("columns", [])]
+
+        # Here we get the list of columns defined in the document, which are the
+        # columns that we will take from each result to assemble the document
+        # object.
+        # When `for_esql=False` is passed below by default, the list will include
+        # nested fields, which ES|QL does not return, causing an error. When passing
+        # `ignore_missing_fields=True` the list will be generated with
+        # `for_esql=True`, so the error will not occur, but the documents will
+        # not have any Nested objects in them.
+        doc_fields = set(cls._get_field_names(for_esql=ignore_missing_fields))
+        if not ignore_missing_fields and not doc_fields.issubset(set(query_columns)):
+            raise ValueError(
+                f"Not all fields of {cls.__name__} were returned by the query. "
+                "Make sure your document does not use Nested fields, which are "
+                "currently not supported in ES|QL. To force the query to be "
+                "evaluated in spite of the missing fields, pass set the "
+                "ignore_missing_fields=True option in the esql_execute() call."
+            )
+        non_doc_fields: set[str] = set(query_columns) - doc_fields - {"_id"}
+        index_id = query_columns.index("_id")
+
+        results = response.body.get("values", [])
+        for column_values in results:
+            # create a dictionary with all the document fields, expanding the
+            # dot notation returned by ES|QL into the recursive dictionaries
+            # used by Document.from_dict()
+            doc_dict: Dict[str, Any] = {}
+            for col, val in zip(query_columns, column_values):
+                if col in doc_fields:
+                    cols = col.split(".")
+                    d = doc_dict
+                    for c in cols[:-1]:
+                        if c not in d:
+                            d[c] = {}
+                        d = d[c]
+                    d[cols[-1]] = val
+
+            # create the document instance
+            obj = cls(meta={"_id": column_values[index_id]})
+            obj._from_dict(doc_dict)
+
+            if return_additional:
+                # build a dict with any other values included in the response
+                other = {
+                    col: val
+                    for col, val in zip(query_columns, column_values)
+                    if col in non_doc_fields
+                }
+
+                yield obj, other
+            else:
+                yield obj

elasticsearch/dsl/_sync/document.py

@@ -21,6 +21,7 @@ from typing import (
     Any,
     Dict,
     Iterable,
+    Iterator,
     List,
     Optional,
     Tuple,
@@ -42,6 +43,7 @@ from .search import Search
 
 if TYPE_CHECKING:
     from elasticsearch import Elasticsearch
+    from elasticsearch.esql.esql import ESQLBase
 
 
 class IndexMeta(DocumentMeta):
@@ -512,3 +514,85 @@ class Document(DocumentBase, metaclass=IndexMeta):
                 return action
 
         return bulk(es, Generate(actions), **kwargs)
+
+    @classmethod
+    def esql_execute(
+        cls,
+        query: "ESQLBase",
+        return_additional: bool = False,
+        ignore_missing_fields: bool = False,
+        using: Optional[UsingType] = None,
+        **kwargs: Any,
+    ) -> Iterator[Union[Self, Tuple[Self, Dict[str, Any]]]]:
+        """
+        Execute the given ES|QL query and return an iterator of 2-element tuples,
+        where the first element is an instance of this ``Document`` and the
+        second a dictionary with any remaining columns requested in the query.
+
+        :arg query: an ES|QL query object created with the ``esql_from()`` method.
+        :arg return_additional: if ``False`` (the default), this method returns
+            document objects. If set to ``True``, the method returns tuples with
+            a document in the first element and a dictionary with any additional
+            columns returned by the query in the second element.
+        :arg ignore_missing_fields: if ``False`` (the default), all the fields of
+            the document must be present in the query, or else an exception is
+            raised. Set to ``True`` to allow missing fields, which will result in
+            partially initialized document objects.
+        :arg using: connection alias to use, defaults to ``'default'``
+        :arg kwargs: additional options for the ``client.esql.query()`` function.
+        """
+        es = cls._get_connection(using)
+        response = es.esql.query(query=str(query), **kwargs)
+        query_columns = [col["name"] for col in response.body.get("columns", [])]
+
+        # Here we get the list of columns defined in the document, which are the
+        # columns that we will take from each result to assemble the document
+        # object.
+        # When `for_esql=False` is passed below by default, the list will include
+        # nested fields, which ES|QL does not return, causing an error. When passing
+        # `ignore_missing_fields=True` the list will be generated with
+        # `for_esql=True`, so the error will not occur, but the documents will
+        # not have any Nested objects in them.
+        doc_fields = set(cls._get_field_names(for_esql=ignore_missing_fields))
+        if not ignore_missing_fields and not doc_fields.issubset(set(query_columns)):
+            raise ValueError(
+                f"Not all fields of {cls.__name__} were returned by the query. "
+                "Make sure your document does not use Nested fields, which are "
+                "currently not supported in ES|QL. To force the query to be "
+                "evaluated in spite of the missing fields, pass set the "
+                "ignore_missing_fields=True option in the esql_execute() call."
+            )
+        non_doc_fields: set[str] = set(query_columns) - doc_fields - {"_id"}
+        index_id = query_columns.index("_id")
+
+        results = response.body.get("values", [])
+        for column_values in results:
+            # create a dictionary with all the document fields, expanding the
+            # dot notation returned by ES|QL into the recursive dictionaries
+            # used by Document.from_dict()
+            doc_dict: Dict[str, Any] = {}
+            for col, val in zip(query_columns, column_values):
+                if col in doc_fields:
+                    cols = col.split(".")
+                    d = doc_dict
+                    for c in cols[:-1]:
+                        if c not in d:
+                            d[c] = {}
+                        d = d[c]
+                    d[cols[-1]] = val
+
+            # create the document instance
+            obj = cls(meta={"_id": column_values[index_id]})
+            obj._from_dict(doc_dict)
+
+            if return_additional:
+                # build a dict with any other values included in the response
+                other = {
+                    col: val
+                    for col, val in zip(query_columns, column_values)
+                    if col in non_doc_fields
+                }
+
+                yield obj, other
+            else:
+                yield obj

elasticsearch/dsl/document_base.py

@@ -49,6 +49,7 @@ from .utils import DOC_META_FIELDS, ObjectBase
 if TYPE_CHECKING:
     from elastic_transport import ObjectApiResponse
 
+    from ..esql.esql import ESQLBase
     from .index_base import IndexBase
 
 
@@ -602,3 +603,44 @@ class DocumentBase(ObjectBase):
 
         meta["_source"] = d
         return meta
+
+    @classmethod
+    def _get_field_names(
+        cls, for_esql: bool = False, nested_class: Optional[type[InnerDoc]] = None
+    ) -> List[str]:
+        """Return the list of field names used by this document.
+        If the document has nested objects, their fields are reported using dot
+        notation. If the ``for_esql`` argument is set to ``True``, the list omits
+        nested fields, which are currently unsupported in ES|QL.
+        """
+        fields = []
+        class_ = nested_class or cls
+        for field_name in class_._doc_type.mapping:
+            field = class_._doc_type.mapping[field_name]
+            if isinstance(field, Object):
+                if for_esql and isinstance(field, Nested):
+                    # ES|QL does not recognize Nested fields at this time
+                    continue
+                sub_fields = cls._get_field_names(
+                    for_esql=for_esql, nested_class=field._doc_class
+                )
+                for sub_field in sub_fields:
+                    fields.append(f"{field_name}.{sub_field}")
+            else:
+                fields.append(field_name)
+        return fields
+
+    @classmethod
+    def esql_from(cls) -> "ESQLBase":
+        """Return a base ES|QL query for instances of this document class.
+
+        The returned query is initialized with ``FROM`` and ``KEEP`` statements,
+        and can be completed as desired.
+        """
+        from ..esql import ESQL  # here to avoid circular imports
+
+        return (
+            ESQL.from_(cls)
+            .metadata("_id")
+            .keep("_id", *tuple(cls._get_field_names(for_esql=True)))
+        )

elasticsearch/dsl/field.py

@@ -119,9 +119,16 @@ class Field(DslBase):
     def __getitem__(self, subfield: str) -> "Field":
         return cast(Field, self._params.get("fields", {})[subfield])
 
-    def _serialize(self, data: Any) -> Any:
+    def _serialize(self, data: Any, skip_empty: bool) -> Any:
         return data
 
+    def _safe_serialize(self, data: Any, skip_empty: bool) -> Any:
+        try:
+            return self._serialize(data, skip_empty)
+        except TypeError:
+            # older method signature, without skip_empty
+            return self._serialize(data)  # type: ignore[call-arg]
+
     def _deserialize(self, data: Any) -> Any:
         return data
 
@@ -133,10 +140,16 @@ class Field(DslBase):
             return AttrList([])
         return self._empty()
 
-    def serialize(self, data: Any) -> Any:
+    def serialize(self, data: Any, skip_empty: bool = True) -> Any:
         if isinstance(data, (list, AttrList, tuple)):
-            return list(map(self._serialize, cast(Iterable[Any], data)))
-        return self._serialize(data)
+            return list(
+                map(
+                    self._safe_serialize,
+                    cast(Iterable[Any], data),
+                    [skip_empty] * len(data),
+                )
+            )
+        return self._safe_serialize(data, skip_empty)
 
     def deserialize(self, data: Any) -> Any:
         if isinstance(data, (list, AttrList, tuple)):
@@ -186,7 +199,7 @@ class RangeField(Field):
         data = {k: self._core_field.deserialize(v) for k, v in data.items()}  # type: ignore[union-attr]
         return Range(data)
 
-    def _serialize(self, data: Any) -> Optional[Dict[str, Any]]:
+    def _serialize(self, data: Any, skip_empty: bool) -> Optional[Dict[str, Any]]:
         if data is None:
             return None
         if not isinstance(data, collections.abc.Mapping):
@@ -550,7 +563,7 @@ class Object(Field):
         return self._wrap(data)
 
     def _serialize(
-        self, data: Optional[Union[Dict[str, Any], "InnerDoc"]]
+        self, data: Optional[Union[Dict[str, Any], "InnerDoc"]], skip_empty: bool
     ) -> Optional[Dict[str, Any]]:
         if data is None:
             return None
@@ -559,7 +572,7 @@ class Object(Field):
         if isinstance(data, collections.abc.Mapping):
             return data
 
-        return data.to_dict()
+        return data.to_dict(skip_empty=skip_empty)
 
     def clean(self, data: Any) -> Any:
         data = super().clean(data)
@@ -768,7 +781,7 @@ class Binary(Field):
     def _deserialize(self, data: Any) -> bytes:
         return base64.b64decode(data)
 
-    def _serialize(self, data: Any) -> Optional[str]:
+    def _serialize(self, data: Any, skip_empty: bool) -> Optional[str]:
         if data is None:
             return None
         return base64.b64encode(data).decode()
@@ -2619,7 +2632,7 @@ class Ip(Field):
         # the ipaddress library for pypy only accepts unicode.
         return ipaddress.ip_address(unicode(data))
 
-    def _serialize(self, data: Any) -> Optional[str]:
+    def _serialize(self, data: Any, skip_empty: bool) -> Optional[str]:
         if data is None:
             return None
         return str(data)
@@ -3367,7 +3380,7 @@ class Percolator(Field):
     def _deserialize(self, data: Any) -> "Query":
         return Q(data)  # type: ignore[no-any-return]
 
-    def _serialize(self, data: Any) -> Optional[Dict[str, Any]]:
+    def _serialize(self, data: Any, skip_empty: bool) -> Optional[Dict[str, Any]]:
         if data is None:
             return None
         return data.to_dict()  # type: ignore[no-any-return]

elasticsearch/dsl/response/aggs.py

@@ -63,7 +63,7 @@ class BucketData(AggResponse[_R]):
         )
 
     def __iter__(self) -> Iterator["Agg"]:  # type: ignore[override]
-        return iter(self.buckets)  # type: ignore[arg-type]
+        return iter(self.buckets)
 
     def __len__(self) -> int:
         return len(self.buckets)