elasticsearch 8.19.0__py3-none-any.whl → 8.19.2__py3-none-any.whl

elasticsearch/dsl/types.py

@@ -170,6 +170,48 @@ class ChiSquareHeuristic(AttrDict[Any]):
         super().__init__(kwargs)
 
 
+class ChunkingSettings(AttrDict[Any]):
+    """
+    :arg strategy: (required) The chunking strategy: `sentence` or `word`.
+        Defaults to `sentence` if omitted.
+    :arg max_chunk_size: (required) The maximum size of a chunk in words.
+        This value cannot be higher than `300` or lower than `20` (for
+        `sentence` strategy) or `10` (for `word` strategy). Defaults to
+        `250` if omitted.
+    :arg overlap: The number of overlapping words for chunks. It is
+        applicable only to a `word` chunking strategy. This value cannot
+        be higher than half the `max_chunk_size` value. Defaults to `100`
+        if omitted.
+    :arg sentence_overlap: The number of overlapping sentences for chunks.
+        It is applicable only for a `sentence` chunking strategy. It can
+        be either `1` or `0`. Defaults to `1` if omitted.
+    """
+
+    strategy: Union[str, DefaultType]
+    max_chunk_size: Union[int, DefaultType]
+    overlap: Union[int, DefaultType]
+    sentence_overlap: Union[int, DefaultType]
+
+    def __init__(
+        self,
+        *,
+        strategy: Union[str, DefaultType] = DEFAULT,
+        max_chunk_size: Union[int, DefaultType] = DEFAULT,
+        overlap: Union[int, DefaultType] = DEFAULT,
+        sentence_overlap: Union[int, DefaultType] = DEFAULT,
+        **kwargs: Any,
+    ):
+        if strategy is not DEFAULT:
+            kwargs["strategy"] = strategy
+        if max_chunk_size is not DEFAULT:
+            kwargs["max_chunk_size"] = max_chunk_size
+        if overlap is not DEFAULT:
+            kwargs["overlap"] = overlap
+        if sentence_overlap is not DEFAULT:
+            kwargs["sentence_overlap"] = sentence_overlap
+        super().__init__(kwargs)
+
+
 class ClassificationInferenceOptions(AttrDict[Any]):
     """
     :arg num_top_classes: Specifies the number of top class predictions to
@@ -2281,9 +2323,7 @@ class LikeDocument(AttrDict[Any]):
     per_field_analyzer: Union[Mapping[Union[str, InstrumentedField], str], DefaultType]
     routing: Union[str, DefaultType]
     version: Union[int, DefaultType]
-    version_type: Union[
-        Literal["internal", "external", "external_gte", "force"], DefaultType
-    ]
+    version_type: Union[Literal["internal", "external", "external_gte"], DefaultType]
 
     def __init__(
         self,
@@ -2298,7 +2338,7 @@ class LikeDocument(AttrDict[Any]):
         routing: Union[str, DefaultType] = DEFAULT,
         version: Union[int, DefaultType] = DEFAULT,
         version_type: Union[
-            Literal["internal", "external", "external_gte", "force"], DefaultType
+            Literal["internal", "external", "external_gte"], DefaultType
         ] = DEFAULT,
         **kwargs: Any,
     ):
@@ -2729,6 +2769,31 @@ class NumericFielddata(AttrDict[Any]):
         super().__init__(kwargs)
 
 
+class PValueHeuristic(AttrDict[Any]):
+    """
+    :arg background_is_superset:
+    :arg normalize_above: Should the results be normalized when above the
+        given value. Allows for consistent significance results at various
+        scales. Note: `0` is a special value which means no normalization
+    """
+
+    background_is_superset: Union[bool, DefaultType]
+    normalize_above: Union[int, DefaultType]
+
+    def __init__(
+        self,
+        *,
+        background_is_superset: Union[bool, DefaultType] = DEFAULT,
+        normalize_above: Union[int, DefaultType] = DEFAULT,
+        **kwargs: Any,
+    ):
+        if background_is_superset is not DEFAULT:
+            kwargs["background_is_superset"] = background_is_superset
+        if normalize_above is not DEFAULT:
+            kwargs["normalize_above"] = normalize_above
+        super().__init__(kwargs)
+
+
 class PercentageScoreHeuristic(AttrDict[Any]):
     pass
 
@@ -3119,6 +3184,26 @@ class ScriptedHeuristic(AttrDict[Any]):
         super().__init__(kwargs)
 
 
+class SemanticTextIndexOptions(AttrDict[Any]):
+    """
+    :arg dense_vector:
+    """
+
+    dense_vector: Union["DenseVectorIndexOptions", Dict[str, Any], DefaultType]
+
+    def __init__(
+        self,
+        *,
+        dense_vector: Union[
+            "DenseVectorIndexOptions", Dict[str, Any], DefaultType
+        ] = DEFAULT,
+        **kwargs: Any,
+    ):
+        if dense_vector is not DEFAULT:
+            kwargs["dense_vector"] = dense_vector
+        super().__init__(kwargs)
+
+
 class ShapeFieldQuery(AttrDict[Any]):
     """
     :arg indexed_shape: Queries using a pre-indexed shape.
@@ -3196,10 +3281,15 @@ class SortOptions(AttrDict[Any]):
 
 class SourceFilter(AttrDict[Any]):
     """
-    :arg excludes:
-    :arg includes:
+    :arg exclude_vectors: If `true`, vector fields are excluded from the
+        returned source.  This option takes precedence over `includes`:
+        any vector field will remain excluded even if it matches an
+        `includes` rule.
+    :arg excludes: A list of fields to exclude from the returned source.
+    :arg includes: A list of fields to include in the returned source.
     """
 
+    exclude_vectors: Union[bool, DefaultType]
     excludes: Union[
         Union[str, InstrumentedField],
         Sequence[Union[str, InstrumentedField]],
@@ -3214,6 +3304,7 @@ class SourceFilter(AttrDict[Any]):
     def __init__(
         self,
         *,
+        exclude_vectors: Union[bool, DefaultType] = DEFAULT,
         excludes: Union[
             Union[str, InstrumentedField],
             Sequence[Union[str, InstrumentedField]],
@@ -3226,6 +3317,8 @@ class SourceFilter(AttrDict[Any]):
         ] = DEFAULT,
         **kwargs: Any,
     ):
+        if exclude_vectors is not DEFAULT:
+            kwargs["exclude_vectors"] = exclude_vectors
         if excludes is not DEFAULT:
             kwargs["excludes"] = str(excludes)
         if includes is not DEFAULT:
@@ -3675,6 +3768,38 @@ class SpanWithinQuery(AttrDict[Any]):
         super().__init__(kwargs)
 
 
+class SparseVectorIndexOptions(AttrDict[Any]):
+    """
+    :arg prune: Whether to perform pruning, omitting the non-significant
+        tokens from the query to improve query performance. If prune is
+        true but the pruning_config is not specified, pruning will occur
+        but default values will be used. Default: false
+    :arg pruning_config: Optional pruning configuration. If enabled, this
+        will omit non-significant tokens from the query in order to
+        improve query performance. This is only used if prune is set to
+        true. If prune is set to true but pruning_config is not specified,
+        default values will be used.
+    """
+
+    prune: Union[bool, DefaultType]
+    pruning_config: Union["TokenPruningConfig", Dict[str, Any], DefaultType]
+
+    def __init__(
+        self,
+        *,
+        prune: Union[bool, DefaultType] = DEFAULT,
+        pruning_config: Union[
+            "TokenPruningConfig", Dict[str, Any], DefaultType
+        ] = DEFAULT,
+        **kwargs: Any,
+    ):
+        if prune is not DEFAULT:
+            kwargs["prune"] = prune
+        if pruning_config is not DEFAULT:
+            kwargs["pruning_config"] = pruning_config
+        super().__init__(kwargs)
+
+
 class SuggestContext(AttrDict[Any]):
     """
     :arg name: (required)
@@ -3713,15 +3838,30 @@ class TDigest(AttrDict[Any]):
     :arg compression: Limits the maximum number of nodes used by the
         underlying TDigest algorithm to `20 * compression`, enabling
         control of memory usage and approximation error.
+    :arg execution_hint: The default implementation of TDigest is
+        optimized for performance, scaling to millions or even billions of
+        sample values while maintaining acceptable accuracy levels (close
+        to 1% relative error for millions of samples in some cases). To
+        use an implementation optimized for accuracy, set this parameter
+        to high_accuracy instead. Defaults to `default` if omitted.
     """
 
     compression: Union[int, DefaultType]
+    execution_hint: Union[Literal["default", "high_accuracy"], DefaultType]
 
     def __init__(
-        self, *, compression: Union[int, DefaultType] = DEFAULT, **kwargs: Any
+        self,
+        *,
+        compression: Union[int, DefaultType] = DEFAULT,
+        execution_hint: Union[
+            Literal["default", "high_accuracy"], DefaultType
+        ] = DEFAULT,
+        **kwargs: Any,
     ):
         if compression is not DEFAULT:
             kwargs["compression"] = compression
+        if execution_hint is not DEFAULT:
+            kwargs["execution_hint"] = execution_hint
         super().__init__(kwargs)
 
 
@@ -3907,24 +4047,25 @@ class TestPopulation(AttrDict[Any]):
 
 class TextEmbedding(AttrDict[Any]):
     """
-    :arg model_id: (required)
     :arg model_text: (required)
+    :arg model_id: Model ID is required for all dense_vector fields but
+        may be inferred for semantic_text fields
     """
 
-    model_id: Union[str, DefaultType]
     model_text: Union[str, DefaultType]
+    model_id: Union[str, DefaultType]
 
     def __init__(
         self,
         *,
-        model_id: Union[str, DefaultType] = DEFAULT,
         model_text: Union[str, DefaultType] = DEFAULT,
+        model_id: Union[str, DefaultType] = DEFAULT,
         **kwargs: Any,
     ):
-        if model_id is not DEFAULT:
-            kwargs["model_id"] = model_id
         if model_text is not DEFAULT:
             kwargs["model_text"] = model_text
+        if model_id is not DEFAULT:
+            kwargs["model_id"] = model_id
         super().__init__(kwargs)
 
 
@@ -4444,7 +4585,7 @@ class ArrayPercentilesItem(AttrDict[Any]):
     :arg value_as_string:
     """
 
-    key: str
+    key: float
     value: Union[float, None]
     value_as_string: str
 
@@ -4555,6 +4696,82 @@ class CardinalityAggregate(AttrDict[Any]):
     meta: Mapping[str, Any]
 
 
+class CartesianBoundsAggregate(AttrDict[Any]):
+    """
+    :arg bounds:
+    :arg meta:
+    """
+
+    bounds: "TopLeftBottomRightGeoBounds"
+    meta: Mapping[str, Any]
+
+
+class CartesianCentroidAggregate(AttrDict[Any]):
+    """
+    :arg count: (required)
+    :arg location:
+    :arg meta:
+    """
+
+    count: int
+    location: "CartesianPoint"
+    meta: Mapping[str, Any]
+
+
+class CartesianPoint(AttrDict[Any]):
+    """
+    :arg x: (required)
+    :arg y: (required)
+    """
+
+    x: float
+    y: float
+
+
+class ChangePointAggregate(AttrDict[Any]):
+    """
+    :arg type: (required)
+    :arg bucket:
+    :arg meta:
+    """
+
+    type: "ChangeType"
+    bucket: "ChangePointBucket"
+    meta: Mapping[str, Any]
+
+
+class ChangePointBucket(AttrDict[Any]):
+    """
+    :arg key: (required)
+    :arg doc_count: (required)
+    """
+
+    key: Union[int, float, str, bool, None, Any]
+    doc_count: int
+
+
+class ChangeType(AttrDict[Any]):
+    """
+    :arg dip:
+    :arg distribution_change:
+    :arg indeterminable:
+    :arg non_stationary:
+    :arg spike:
+    :arg stationary:
+    :arg step_change:
+    :arg trend_change:
+    """
+
+    dip: "Dip"
+    distribution_change: "DistributionChange"
+    indeterminable: "Indeterminable"
+    non_stationary: "NonStationary"
+    spike: "Spike"
+    stationary: "Stationary"
+    step_change: "StepChange"
+    trend_change: "TrendChange"
+
+
 class ChildrenAggregate(AttrDict[Any]):
     """
     :arg doc_count: (required)
@@ -4832,6 +5049,26 @@ class DfsStatisticsProfile(AttrDict[Any]):
     children: Sequence["DfsStatisticsProfile"]
 
 
+class Dip(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg change_point: (required)
+    """
+
+    p_value: float
+    change_point: int
+
+
+class DistributionChange(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg change_point: (required)
+    """
+
+    p_value: float
+    change_point: int
+
+
 class DoubleTermsAggregate(AttrDict[Any]):
     """
     Result of a `terms` aggregation when the field is some kind of decimal
@@ -5290,7 +5527,9 @@ class HdrPercentileRanksAggregate(AttrDict[Any]):
     :arg meta:
     """
 
-    values: Union[Mapping[str, Union[str, int, None]], Sequence["ArrayPercentilesItem"]]
+    values: Union[
+        Mapping[str, Union[str, float, None]], Sequence["ArrayPercentilesItem"]
+    ]
     meta: Mapping[str, Any]
 
 
@@ -5300,7 +5539,9 @@ class HdrPercentilesAggregate(AttrDict[Any]):
     :arg meta:
     """
 
-    values: Union[Mapping[str, Union[str, int, None]], Sequence["ArrayPercentilesItem"]]
+    values: Union[
+        Mapping[str, Union[str, float, None]], Sequence["ArrayPercentilesItem"]
+    ]
     meta: Mapping[str, Any]
 
 
@@ -5391,6 +5632,14 @@ class HitsMetadata(AttrDict[Any]):
     max_score: Union[float, None]
 
 
+class Indeterminable(AttrDict[Any]):
+    """
+    :arg reason: (required)
+    """
+
+    reason: str
+
+
 class InferenceAggregate(AttrDict[Any]):
     """
     :arg value:
@@ -5793,6 +6042,18 @@ class NestedIdentity(AttrDict[Any]):
     _nested: "NestedIdentity"
 
 
+class NonStationary(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg r_value: (required)
+    :arg trend: (required)
+    """
+
+    p_value: float
+    r_value: float
+    trend: str
+
+
 class ParentAggregate(AttrDict[Any]):
     """
     :arg doc_count: (required)
@@ -5809,7 +6070,9 @@ class PercentilesBucketAggregate(AttrDict[Any]):
     :arg meta:
     """
 
-    values: Union[Mapping[str, Union[str, int, None]], Sequence["ArrayPercentilesItem"]]
+    values: Union[
+        Mapping[str, Union[str, float, None]], Sequence["ArrayPercentilesItem"]
+    ]
     meta: Mapping[str, Any]
 
 
@@ -6010,17 +6273,19 @@ class SearchProfile(AttrDict[Any]):
 class ShardFailure(AttrDict[Any]):
     """
     :arg reason: (required)
-    :arg shard: (required)
     :arg index:
     :arg node:
+    :arg shard:
     :arg status:
+    :arg primary:
     """
 
     reason: "ErrorCause"
-    shard: int
     index: str
     node: str
+    shard: int
     status: str
+    primary: bool
 
 
 class ShardProfile(AttrDict[Any]):
@@ -6146,6 +6411,16 @@ class SimpleValueAggregate(AttrDict[Any]):
     meta: Mapping[str, Any]
 
 
+class Spike(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg change_point: (required)
+    """
+
+    p_value: float
+    change_point: int
+
+
 class StandardDeviationBounds(AttrDict[Any]):
     """
     :arg upper: (required)
@@ -6182,6 +6457,10 @@ class StandardDeviationBoundsAsString(AttrDict[Any]):
     lower_sampling: str
 
 
+class Stationary(AttrDict[Any]):
+    pass
+
+
 class StatsAggregate(AttrDict[Any]):
     """
     Statistics aggregation result. `min`, `max` and `avg` are missing if
@@ -6237,6 +6516,16 @@ class StatsBucketAggregate(AttrDict[Any]):
     meta: Mapping[str, Any]
 
 
+class StepChange(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg change_point: (required)
+    """
+
+    p_value: float
+    change_point: int
+
+
 class StringRareTermsAggregate(AttrDict[Any]):
     """
     Result of the `rare_terms` aggregation when the field is a string.
@@ -6344,7 +6633,9 @@ class TDigestPercentileRanksAggregate(AttrDict[Any]):
     :arg meta:
     """
 
-    values: Union[Mapping[str, Union[str, int, None]], Sequence["ArrayPercentilesItem"]]
+    values: Union[
+        Mapping[str, Union[str, float, None]], Sequence["ArrayPercentilesItem"]
+    ]
     meta: Mapping[str, Any]
 
 
@@ -6354,7 +6645,9 @@ class TDigestPercentilesAggregate(AttrDict[Any]):
     :arg meta:
     """
 
-    values: Union[Mapping[str, Union[str, int, None]], Sequence["ArrayPercentilesItem"]]
+    values: Union[
+        Mapping[str, Union[str, float, None]], Sequence["ArrayPercentilesItem"]
+    ]
     meta: Mapping[str, Any]
 
 
@@ -6464,6 +6757,18 @@ class TotalHits(AttrDict[Any]):
     value: int
 
 
+class TrendChange(AttrDict[Any]):
+    """
+    :arg p_value: (required)
+    :arg r_value: (required)
+    :arg change_point: (required)
+    """
+
+    p_value: float
+    r_value: float
+    change_point: int
+
+
 class UnmappedRareTermsAggregate(AttrDict[Any]):
     """
     Result of a `rare_terms` aggregation when the field is unmapped.

elasticsearch/dsl/utils.py

@@ -603,7 +603,7 @@ class ObjectBase(AttrDict[Any]):
             # if this is a mapped field,
             f = self.__get_field(k)
             if f and f._coerce:
-                v = f.serialize(v)
+                v = f.serialize(v, skip_empty=skip_empty)
 
             # if someone assigned AttrList, unwrap it
             if isinstance(v, AttrList):

elasticsearch/esql/__init__.py

@@ -15,4 +15,5 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
-from .esql import ESQL, and_, not_, or_  # noqa: F401
+from ..dsl import E  # noqa: F401
+from .esql import ESQL, ESQLBase, and_, not_, or_  # noqa: F401