elasticsearch 9.1.1__py3-none-any.whl → 9.1.2__py3-none-any.whl

elasticsearch/dsl/aggs.py

@@ -653,6 +653,54 @@ class Cardinality(Agg[_R]):
         )
 
 
+class CartesianBounds(Agg[_R]):
+    """
+    A metric aggregation that computes the spatial bounding box containing
+    all values for a Point or Shape field.
+
+    :arg field: The field on which to run the aggregation.
+    :arg missing: The value to apply to documents that do not have a
+        value. By default, documents without a value are ignored.
+    :arg script:
+    """
+
+    name = "cartesian_bounds"
+
+    def __init__(
+        self,
+        *,
+        field: Union[str, "InstrumentedField", "DefaultType"] = DEFAULT,
+        missing: Union[str, int, float, bool, "DefaultType"] = DEFAULT,
+        script: Union["types.Script", Dict[str, Any], "DefaultType"] = DEFAULT,
+        **kwargs: Any,
+    ):
+        super().__init__(field=field, missing=missing, script=script, **kwargs)
+
+
+class CartesianCentroid(Agg[_R]):
+    """
+    A metric aggregation that computes the weighted centroid from all
+    coordinate values for point and shape fields.
+
+    :arg field: The field on which to run the aggregation.
+    :arg missing: The value to apply to documents that do not have a
+        value. By default, documents without a value are ignored.
+    :arg script:
+    """
+
+    name = "cartesian_centroid"
+
+    def __init__(
+        self,
+        *,
+        field: Union[str, "InstrumentedField", "DefaultType"] = DEFAULT,
+        missing: Union[str, int, float, bool, "DefaultType"] = DEFAULT,
+        script: Union["types.Script", Dict[str, Any], "DefaultType"] = DEFAULT,
+        **kwargs: Any,
+    ):
+        super().__init__(field=field, missing=missing, script=script, **kwargs)
+
+
 class CategorizeText(Bucket[_R]):
     """
     A multi-bucket aggregation that groups semi-structured text into
@@ -735,6 +783,43 @@ class CategorizeText(Bucket[_R]):
         )
 
 
+class ChangePoint(Pipeline[_R]):
+    """
+    A sibling pipeline that detects, spikes, dips, and change points in a
+    metric. Given a distribution of values provided by the sibling multi-
+    bucket aggregation, this aggregation indicates the bucket of any spike
+    or dip and/or the bucket at which the largest change in the
+    distribution of values, if they are statistically significant. There
+    must be at least 22 bucketed values. Fewer than 1,000 is preferred.
+
+    :arg format: `DecimalFormat` pattern for the output value. If
+        specified, the formatted value is returned in the aggregation’s
+        `value_as_string` property.
+    :arg gap_policy: Policy to apply when gaps are found in the data.
+        Defaults to `skip` if omitted.
+    :arg buckets_path: Path to the buckets that contain one set of values
+        to correlate.
+    """
+
+    name = "change_point"
+
+    def __init__(
+        self,
+        *,
+        format: Union[str, "DefaultType"] = DEFAULT,
+        gap_policy: Union[
+            Literal["skip", "insert_zeros", "keep_values"], "DefaultType"
+        ] = DEFAULT,
+        buckets_path: Union[
+            str, Sequence[str], Mapping[str, str], "DefaultType"
+        ] = DEFAULT,
+        **kwargs: Any,
+    ):
+        super().__init__(
+            format=format, gap_policy=gap_policy, buckets_path=buckets_path, **kwargs
+        )
+
+
 class Children(Bucket[_R]):
     """
     A single bucket aggregation that selects child documents that have the
@@ -2980,6 +3065,14 @@ class SignificantTerms(Bucket[_R]):
         the foreground sample with a term divided by the number of
         documents in the background with the term.
     :arg script_heuristic: Customized score, implemented via a script.
+    :arg p_value: Significant terms heuristic that calculates the p-value
+        between the term existing in foreground and background sets.  The
+        p-value is the probability of obtaining test results at least as
+        extreme as the results actually observed, under the assumption
+        that the null hypothesis is correct. The p-value is calculated
+        assuming that the foreground set and the background set are
+        independent https://en.wikipedia.org/wiki/Bernoulli_trial, with
+        the null hypothesis that the probabilities are the same.
     :arg shard_min_doc_count: Regulates the certainty a shard has if the
         term should actually be added to the candidate list or not with
         respect to the `min_doc_count`. Terms will only be considered if
@@ -3033,6 +3126,9 @@ class SignificantTerms(Bucket[_R]):
         script_heuristic: Union[
             "types.ScriptedHeuristic", Dict[str, Any], "DefaultType"
         ] = DEFAULT,
+        p_value: Union[
+            "types.PValueHeuristic", Dict[str, Any], "DefaultType"
+        ] = DEFAULT,
         shard_min_doc_count: Union[int, "DefaultType"] = DEFAULT,
         shard_size: Union[int, "DefaultType"] = DEFAULT,
         size: Union[int, "DefaultType"] = DEFAULT,
@@ -3051,6 +3147,7 @@ class SignificantTerms(Bucket[_R]):
             mutual_information=mutual_information,
             percentage=percentage,
             script_heuristic=script_heuristic,
+            p_value=p_value,
             shard_min_doc_count=shard_min_doc_count,
             shard_size=shard_size,
             size=size,

elasticsearch/dsl/document_base.py

@@ -34,6 +34,11 @@ from typing import (
     overload,
 )
 
+try:
+    import annotationlib
+except ImportError:
+    annotationlib = None
+
 try:
     from types import UnionType
 except ImportError:
@@ -332,6 +337,16 @@ class DocumentOptions:
         #     # ignore attributes
         #     field10: ClassVar[string] = "a regular class variable"
         annotations = attrs.get("__annotations__", {})
+        if not annotations and annotationlib:
+            # Python 3.14+ uses annotationlib
+            annotate = annotationlib.get_annotate_from_class_namespace(attrs)
+            if annotate:
+                annotations = (
+                    annotationlib.call_annotate_function(
+                        annotate, format=annotationlib.Format.VALUE
+                    )
+                    or {}
+                )
         fields = {n for n in attrs if isinstance(attrs[n], Field)}
         fields.update(annotations.keys())
         field_defaults = {}

elasticsearch/dsl/field.py

@@ -572,7 +572,11 @@ class Object(Field):
         if isinstance(data, collections.abc.Mapping):
             return data
 
-        return data.to_dict(skip_empty=skip_empty)
+        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)
@@ -3862,14 +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,
@@ -3877,9 +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:
@@ -3888,8 +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/types.py

@@ -151,9 +151,10 @@ class ChunkingSettings(AttrDict[Any]):
         strategies in the linked documentation. 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.
+        This value cannot be lower than `20` (for `sentence` strategy) or
+        `10` (for `word` strategy). This value should not exceed the
+        window size for the associated model. Defaults to `250` if
+        omitted.
     :arg separator_group: Only applicable to the `recursive` strategy and
         required when using it.  Sets a predefined list of separators in
         the saved chunking settings based on the selected text type.
@@ -397,14 +398,17 @@ class DenseVectorIndexOptions(AttrDict[Any]):
         HNSW graph.  Only applicable to `hnsw`, `int8_hnsw`, `bbq_hnsw`,
         and `int4_hnsw` index types. Defaults to `16` if omitted.
     :arg rescore_vector: The rescore vector options. This is only
-        applicable to `bbq_hnsw`, `int4_hnsw`, `int8_hnsw`, `bbq_flat`,
-        `int4_flat`, and `int8_flat` index types.
+        applicable to `bbq_disk`, `bbq_hnsw`, `int4_hnsw`, `int8_hnsw`,
+        `bbq_flat`, `int4_flat`, and `int8_flat` index types.
+    :arg on_disk_rescore: `true` if vector rescoring should be done on-
+        disk  Only applicable to `bbq_hnsw`
     """
 
     type: Union[
         Literal[
             "bbq_flat",
             "bbq_hnsw",
+            "bbq_disk",
             "flat",
             "hnsw",
             "int4_flat",
@@ -420,6 +424,7 @@ class DenseVectorIndexOptions(AttrDict[Any]):
     rescore_vector: Union[
         "DenseVectorIndexOptionsRescoreVector", Dict[str, Any], DefaultType
     ]
+    on_disk_rescore: Union[bool, DefaultType]
 
     def __init__(
         self,
@@ -428,6 +433,7 @@ class DenseVectorIndexOptions(AttrDict[Any]):
             Literal[
                 "bbq_flat",
                 "bbq_hnsw",
+                "bbq_disk",
                 "flat",
                 "hnsw",
                 "int4_flat",
@@ -443,6 +449,7 @@ class DenseVectorIndexOptions(AttrDict[Any]):
         rescore_vector: Union[
             "DenseVectorIndexOptionsRescoreVector", Dict[str, Any], DefaultType
         ] = DEFAULT,
+        on_disk_rescore: Union[bool, DefaultType] = DEFAULT,
         **kwargs: Any,
     ):
         if type is not DEFAULT:
@@ -455,6 +462,8 @@ class DenseVectorIndexOptions(AttrDict[Any]):
             kwargs["m"] = m
         if rescore_vector is not DEFAULT:
             kwargs["rescore_vector"] = rescore_vector
+        if on_disk_rescore is not DEFAULT:
+            kwargs["on_disk_rescore"] = on_disk_rescore
         super().__init__(kwargs)
 
 
@@ -2326,9 +2335,7 @@ 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,
@@ -2343,7 +2350,7 @@ 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,
     ):
@@ -2774,6 +2781,31 @@ 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
 
@@ -3164,6 +3196,33 @@ class ScriptedHeuristic(AttrDict[Any]):
         super().__init__(kwargs)
 
 
+class SemanticTextIndexOptions(AttrDict[Any]):
+    """
+    :arg dense_vector:
+    :arg sparse_vector:
+    """
+
+    dense_vector: Union["DenseVectorIndexOptions", Dict[str, Any], DefaultType]
+    sparse_vector: Union["SparseVectorIndexOptions", Dict[str, Any], DefaultType]
+
+    def __init__(
+        self,
+        *,
+        dense_vector: Union[
+            "DenseVectorIndexOptions", Dict[str, Any], DefaultType
+        ] = DEFAULT,
+        sparse_vector: Union[
+            "SparseVectorIndexOptions", Dict[str, Any], DefaultType
+        ] = DEFAULT,
+        **kwargs: Any,
+    ):
+        if dense_vector is not DEFAULT:
+            kwargs["dense_vector"] = dense_vector
+        if sparse_vector is not DEFAULT:
+            kwargs["sparse_vector"] = sparse_vector
+        super().__init__(kwargs)
+
+
 class ShapeFieldQuery(AttrDict[Any]):
     """
     :arg indexed_shape: Queries using a pre-indexed shape.
@@ -4009,24 +4068,25 @@ 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)
 
 
@@ -4659,6 +4719,82 @@ 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]
+    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)
@@ -4936,6 +5072,26 @@ 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
@@ -5497,6 +5653,14 @@ class HitsMetadata(AttrDict[Any]):
     max_score: Union[float, None]
 
 
+class Indeterminable(AttrDict[Any]):
+    """
+    :arg reason: (required)
+    """
+
+    reason: str
+
+
 class InferenceAggregate(AttrDict[Any]):
     """
     :arg value:
@@ -5899,6 +6063,18 @@ 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)
@@ -6256,6 +6432,16 @@ 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)
@@ -6292,6 +6478,10 @@ 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
@@ -6347,6 +6537,16 @@ 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.
@@ -6578,6 +6778,18 @@ 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/helpers/__init__.py

@@ -19,12 +19,21 @@ from .._async.helpers import async_bulk, async_reindex, async_scan, async_stream
 from .._utils import fixup_module_metadata
 from .actions import _chunk_actions  # noqa: F401
 from .actions import _process_bulk_chunk  # noqa: F401
-from .actions import bulk, expand_action, parallel_bulk, reindex, scan, streaming_bulk
+from .actions import (
+    BULK_FLUSH,
+    bulk,
+    expand_action,
+    parallel_bulk,
+    reindex,
+    scan,
+    streaming_bulk,
+)
 from .errors import BulkIndexError, ScanError
 
 __all__ = [
     "BulkIndexError",
     "ScanError",
+    "BULK_FLUSH",
     "expand_action",
     "streaming_bulk",
     "bulk",