elasticsearch 9.1.0__py3-none-any.whl → 9.1.2__py3-none-any.whl

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 +572,11 @@ class Object(Field):
         if isinstance(data, collections.abc.Mapping):
             return data
 
-        return data.to_dict()
+        try:
+            return data.to_dict(skip_empty=skip_empty)
+        except TypeError:
+            # this would only happen if an AttrDict was given instead of an InnerDoc
+            return data.to_dict()
 
     def clean(self, data: Any) -> Any:
         data = super().clean(data)
@@ -768,7 +785,7 @@ 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 +2636,7 @@ 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 +3384,7 @@ 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]
@@ -3849,14 +3866,21 @@ class SemanticText(Field):
         by using the Update mapping API. Use the Create inference API to
         create the endpoint. If not specified, the inference endpoint
         defined by inference_id will be used at both index and query time.
+    :arg index_options: Settings for index_options that override any
+        defaults used by semantic_text, for example specific quantization
+        settings.
     :arg chunking_settings: Settings for chunking text into smaller
         passages. If specified, these will override the chunking settings
         sent in the inference endpoint associated with inference_id. If
         chunking settings are updated, they will not be applied to
         existing documents until they are reindexed.
+    :arg fields:
     """
 
     name = "semantic_text"
+    _param_defs = {
+        "fields": {"type": "field", "hash": True},
+    }
 
     def __init__(
         self,
@@ -3864,9 +3888,13 @@ class SemanticText(Field):
         meta: Union[Mapping[str, str], "DefaultType"] = DEFAULT,
         inference_id: Union[str, "DefaultType"] = DEFAULT,
         search_inference_id: Union[str, "DefaultType"] = DEFAULT,
+        index_options: Union[
+            "types.SemanticTextIndexOptions", Dict[str, Any], "DefaultType"
+        ] = DEFAULT,
         chunking_settings: Union[
-            "types.ChunkingSettings", Dict[str, Any], "DefaultType"
+            "types.ChunkingSettings", None, Dict[str, Any], "DefaultType"
         ] = DEFAULT,
+        fields: Union[Mapping[str, Field], "DefaultType"] = DEFAULT,
         **kwargs: Any,
     ):
         if meta is not DEFAULT:
@@ -3875,8 +3903,12 @@ class SemanticText(Field):
             kwargs["inference_id"] = inference_id
         if search_inference_id is not DEFAULT:
             kwargs["search_inference_id"] = search_inference_id
+        if index_options is not DEFAULT:
+            kwargs["index_options"] = index_options
         if chunking_settings is not DEFAULT:
             kwargs["chunking_settings"] = chunking_settings
+        if fields is not DEFAULT:
+            kwargs["fields"] = fields
         super().__init__(*args, **kwargs)
 
 

elasticsearch/dsl/query.py

@@ -1079,6 +1079,8 @@ class Knn(Query):
         a query_vector_builder or query_vector, but not both.
     :arg num_candidates: The number of nearest neighbor candidates to
         consider per shard
+    :arg visit_percentage: The percentage of vectors to explore per shard
+        while doing knn search with bbq_disk
     :arg k: The final number of nearest neighbors to return as top hits
     :arg filter: Filters for the kNN search query
     :arg similarity: The minimum similarity for a vector to be considered
@@ -1107,6 +1109,7 @@ class Knn(Query):
             "types.QueryVectorBuilder", Dict[str, Any], "DefaultType"
         ] = DEFAULT,
         num_candidates: Union[int, "DefaultType"] = DEFAULT,
+        visit_percentage: Union[float, "DefaultType"] = DEFAULT,
         k: Union[int, "DefaultType"] = DEFAULT,
         filter: Union[Query, Sequence[Query], "DefaultType"] = DEFAULT,
         similarity: Union[float, "DefaultType"] = DEFAULT,
@@ -1122,6 +1125,7 @@ class Knn(Query):
             query_vector=query_vector,
             query_vector_builder=query_vector_builder,
             num_candidates=num_candidates,
+            visit_percentage=visit_percentage,
             k=k,
             filter=filter,
             similarity=similarity,
@@ -1433,7 +1437,7 @@ class MoreLikeThis(Query):
         ] = DEFAULT,
         version: Union[int, "DefaultType"] = DEFAULT,
         version_type: Union[
-            Literal["internal", "external", "external_gte", "force"], "DefaultType"
+            Literal["internal", "external", "external_gte"], "DefaultType"
         ] = DEFAULT,
         boost: Union[float, "DefaultType"] = DEFAULT,
         _name: Union[str, "DefaultType"] = DEFAULT,

elasticsearch/dsl/response/__init__.py

@@ -233,10 +233,13 @@ AggregateResponseType = Union[
     "types.SimpleValueAggregate",
     "types.DerivativeAggregate",
     "types.BucketMetricValueAggregate",
+    "types.ChangePointAggregate",
     "types.StatsAggregate",
     "types.StatsBucketAggregate",
     "types.ExtendedStatsAggregate",
     "types.ExtendedStatsBucketAggregate",
+    "types.CartesianBoundsAggregate",
+    "types.CartesianCentroidAggregate",
     "types.GeoBoundsAggregate",
     "types.GeoCentroidAggregate",
     "types.HistogramAggregate",

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)