elasticsearch 9.1.3__py3-none-any.whl → 9.2.1__py3-none-any.whl

elasticsearch/_sync/client/license.py

@@ -104,8 +104,10 @@ class LicenseClient(NamespacedClient):
             license types. If `false`, this parameter returns platinum for both platinum
             and enterprise license types. This behavior is maintained for backwards compatibility.
             This parameter is deprecated and will always be set to true in 8.x.
-        :param local: Specifies whether to retrieve local information. The default value
-            is `false`, which means the information is retrieved from the master node.
+        :param local: Specifies whether to retrieve local information. From 9.2 onwards
+            the default value is `true`, which means the information is retrieved from
+            the responding node. In earlier versions the default is `false`, which means
+            the information is retrieved from the elected master node.
         """
         __path_parts: t.Dict[str, str] = {}
         __path = "/_license"

elasticsearch/_sync/client/ml.py

@@ -2397,7 +2397,7 @@ class MlClient(NamespacedClient):
         exclude_interim: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         human: t.Optional[bool] = None,
-        overall_score: t.Optional[t.Union[float, str]] = None,
+        overall_score: t.Optional[float] = None,
         pretty: t.Optional[bool] = None,
         start: t.Optional[t.Union[str, t.Any]] = None,
         top_n: t.Optional[int] = None,
@@ -5755,7 +5755,7 @@ class MlClient(NamespacedClient):
           <p>Validate an anomaly detection job.</p>
 
 
-        `<https://www.elastic.co/guide/en/machine-learning/9.1/ml-jobs.html>`_
+        `<https://www.elastic.co/guide/en/machine-learning/9.2/ml-jobs.html>`_
 
         :param analysis_config:
         :param analysis_limits:

elasticsearch/_sync/client/nodes.py

@@ -368,9 +368,7 @@ class NodesClient(NamespacedClient):
         human: t.Optional[bool] = None,
         include_segment_file_sizes: t.Optional[bool] = None,
         include_unloaded_segments: t.Optional[bool] = None,
-        level: t.Optional[
-            t.Union[str, t.Literal["cluster", "indices", "shards"]]
-        ] = None,
+        level: t.Optional[t.Union[str, t.Literal["indices", "node", "shards"]]] = None,
         pretty: t.Optional[bool] = None,
         timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         types: t.Optional[t.Sequence[str]] = None,
@@ -387,7 +385,7 @@ class NodesClient(NamespacedClient):
 
         :param node_id: Comma-separated list of node IDs or names used to limit returned
             information.
-        :param metric:
+        :param metric: Limits the information returned to the specific metrics.
         :param index_metric: Limit the information returned for indices metric to the
             specific index metrics. It can be used only if indices (or all) metric is
             specified.

elasticsearch/_sync/client/project.py

@@ -0,0 +1,68 @@
+#  Licensed to Elasticsearch B.V. under one or more contributor
+#  license agreements. See the NOTICE file distributed with
+#  this work for additional information regarding copyright
+#  ownership. Elasticsearch B.V. licenses this file to you under
+#  the Apache License, Version 2.0 (the "License"); you may
+#  not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+# 	http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing,
+#  software distributed under the License is distributed on an
+#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+#  KIND, either express or implied.  See the License for the
+#  specific language governing permissions and limitations
+#  under the License.
+
+import typing as t
+
+from elastic_transport import ObjectApiResponse
+
+from ._base import NamespacedClient
+from .utils import (
+    Stability,
+    _availability_warning,
+    _rewrite_parameters,
+)
+
+
+class ProjectClient(NamespacedClient):
+
+    @_rewrite_parameters()
+    @_availability_warning(Stability.EXPERIMENTAL)
+    def tags(
+        self,
+        *,
+        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,
+    ) -> ObjectApiResponse[t.Any]:
+        """
+        .. raw:: html
+
+          <p>Get tags.</p>
+          <p>Get the tags that are defined for the project.</p>
+
+        """
+        __path_parts: t.Dict[str, str] = {}
+        __path = "/_project/tags"
+        __query: t.Dict[str, t.Any] = {}
+        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
+        __headers = {"accept": "application/json"}
+        return self.perform_request(  # type: ignore[return-value]
+            "GET",
+            __path,
+            params=__query,
+            headers=__headers,
+            endpoint_id="project.tags",
+            path_parts=__path_parts,
+        )

elasticsearch/_sync/client/security.py

@@ -2052,6 +2052,45 @@ class SecurityClient(NamespacedClient):
             path_parts=__path_parts,
         )
 
+    @_rewrite_parameters()
+    def get_stats(
+        self,
+        *,
+        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,
+    ) -> ObjectApiResponse[t.Any]:
+        """
+        .. raw:: html
+
+          <p>Get security stats.</p>
+          <p>Gather security usage statistics from all node(s) within the cluster.</p>
+
+
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-security-get-stats>`_
+        """
+        __path_parts: t.Dict[str, str] = {}
+        __path = "/_security/stats"
+        __query: t.Dict[str, t.Any] = {}
+        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
+        __headers = {"accept": "application/json"}
+        return self.perform_request(  # type: ignore[return-value]
+            "GET",
+            __path,
+            params=__query,
+            headers=__headers,
+            endpoint_id="security.get_stats",
+            path_parts=__path_parts,
+        )
+
     @_rewrite_parameters(
         body_fields=(
             "grant_type",

elasticsearch/_sync/client/shutdown.py

@@ -22,6 +22,9 @@ from elastic_transport import ObjectApiResponse
 from ._base import NamespacedClient
 from .utils import (
     SKIP_IN_PATH,
+    Stability,
+    Visibility,
+    _availability_warning,
     _quote,
     _rewrite_parameters,
 )
@@ -30,6 +33,7 @@ from .utils import (
 class ShutdownClient(NamespacedClient):
 
     @_rewrite_parameters()
+    @_availability_warning(Stability.STABLE, Visibility.PRIVATE)
     def delete_node(
         self,
         *,
@@ -90,6 +94,7 @@ class ShutdownClient(NamespacedClient):
         )
 
     @_rewrite_parameters()
+    @_availability_warning(Stability.STABLE, Visibility.PRIVATE)
     def get_node(
         self,
         *,
@@ -149,6 +154,7 @@ class ShutdownClient(NamespacedClient):
     @_rewrite_parameters(
         body_fields=("reason", "type", "allocation_delay", "target_node_name"),
     )
+    @_availability_warning(Stability.STABLE, Visibility.PRIVATE)
     def put_node(
         self,
         *,

elasticsearch/_sync/client/simulate.py

@@ -56,6 +56,7 @@ class SimulateClient(NamespacedClient):
             t.Mapping[str, t.Mapping[str, t.Any]]
         ] = None,
         mapping_addition: t.Optional[t.Mapping[str, t.Any]] = None,
+        merge_type: t.Optional[t.Union[str, t.Literal["index", "template"]]] = None,
         pipeline: t.Optional[str] = None,
         pipeline_substitutions: t.Optional[
             t.Mapping[str, t.Mapping[str, t.Any]]
@@ -93,6 +94,11 @@ class SimulateClient(NamespacedClient):
         :param index_template_substitutions: A map of index template names to substitute
             index template definition objects.
         :param mapping_addition:
+        :param merge_type: The mapping merge type if mapping overrides are being provided
+            in mapping_addition. The allowed values are one of index or template. The
+            index option merges mappings the way they would be merged into an existing
+            index. The template option merges mappings the way they would be merged into
+            a template.
         :param pipeline: The pipeline to use as the default pipeline. This value can
             be used to override the default pipeline of the index.
         :param pipeline_substitutions: Pipelines to test. If you don’t specify the `pipeline`
@@ -116,6 +122,8 @@ class SimulateClient(NamespacedClient):
             __query["filter_path"] = filter_path
         if human is not None:
             __query["human"] = human
+        if merge_type is not None:
+            __query["merge_type"] = merge_type
         if pipeline is not None:
             __query["pipeline"] = pipeline
         if pretty is not None:

elasticsearch/_sync/client/snapshot.py

@@ -872,35 +872,40 @@ class SnapshotClient(NamespacedClient):
 
         :param name: The name of the repository.
         :param blob_count: The total number of blobs to write to the repository during
-            the test. For realistic experiments, you should set it to at least `2000`.
+            the test. For realistic experiments, set this parameter to at least `2000`.
         :param concurrency: The number of operations to run concurrently during the test.
+            For realistic experiments, leave this parameter unset.
         :param detailed: Indicates whether to return detailed results, including timing
             information for every operation performed during the analysis. If false,
             it returns only a summary of the analysis.
         :param early_read_node_count: The number of nodes on which to perform an early
             read operation while writing each blob. Early read operations are only rarely
-            performed.
+            performed. For realistic experiments, leave this parameter unset.
         :param max_blob_size: The maximum size of a blob to be written during the test.
-            For realistic experiments, you should set it to at least `2gb`.
+            For realistic experiments, set this parameter to at least `2gb`.
         :param max_total_data_size: An upper limit on the total size of all the blobs
-            written during the test. For realistic experiments, you should set it to
+            written during the test. For realistic experiments, set this parameter to
             at least `1tb`.
         :param rare_action_probability: The probability of performing a rare action such
-            as an early read, an overwrite, or an aborted write on each blob.
+            as an early read, an overwrite, or an aborted write on each blob. For realistic
+            experiments, leave this parameter unset.
         :param rarely_abort_writes: Indicates whether to rarely cancel writes before
-            they complete.
+            they complete. For realistic experiments, leave this parameter unset.
         :param read_node_count: The number of nodes on which to read a blob after writing.
+            For realistic experiments, leave this parameter unset.
         :param register_operation_count: The minimum number of linearizable register
-            operations to perform in total. For realistic experiments, you should set
-            it to at least `100`.
+            operations to perform in total. For realistic experiments, set this parameter
+            to at least `100`.
         :param seed: The seed for the pseudo-random number generator used to generate
             the list of operations performed during the test. To repeat the same set
             of operations in multiple experiments, use the same seed in each experiment.
             Note that the operations are performed concurrently so might not always happen
-            in the same order on each run.
+            in the same order on each run. For realistic experiments, leave this parameter
+            unset.
         :param timeout: The period of time to wait for the test to complete. If no response
             is received before the timeout expires, the test is cancelled and returns
-            an error.
+            an error. For realistic experiments, set this parameter sufficiently long
+            to allow the test to complete.
         """
         if name in SKIP_IN_PATH:
             raise ValueError("Empty value passed for parameter 'name'")
@@ -1266,6 +1271,11 @@ class SnapshotClient(NamespacedClient):
           <p>If you omit the <code>&lt;snapshot&gt;</code> request path parameter, the request retrieves information only for currently running snapshots.
           This usage is preferred.
           If needed, you can specify <code>&lt;repository&gt;</code> and <code>&lt;snapshot&gt;</code> to retrieve information for specific snapshots, even if they're not currently running.</p>
+          <p>Note that the stats will not be available for any shard snapshots in an ongoing snapshot completed by a node that (even momentarily) left the cluster.
+          Loading the stats from the repository is an expensive operation (see the WARNING below).
+          Therefore the stats values for such shards will be -1 even though the &quot;stage&quot; value will be &quot;DONE&quot;, in order to minimize latency.
+          A &quot;description&quot; field will be present for a shard snapshot completed by a departed node explaining why the shard snapshot's stats results are invalid.
+          Consequently, the total stats for the index will be less than expected due to the missing values from these shards.</p>
           <p>WARNING: Using the API to return the status of any snapshots other than currently running snapshots can be expensive.
           The API requires a read from the repository for each shard in each snapshot.
           For example, if you have 100 snapshots with 1,000 shards each, an API request that includes all snapshots will require 100,000 reads (100 snapshots x 1,000 shards).</p>

elasticsearch/_sync/client/sql.py

@@ -285,6 +285,7 @@ class SqlClient(NamespacedClient):
         page_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         params: t.Optional[t.Sequence[t.Any]] = None,
         pretty: t.Optional[bool] = None,
+        project_routing: t.Optional[str] = None,
         query: t.Optional[str] = None,
         request_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         runtime_mappings: t.Optional[t.Mapping[str, t.Mapping[str, t.Any]]] = None,
@@ -332,6 +333,10 @@ class SqlClient(NamespacedClient):
             is no longer available. Subsequent scroll requests prolong the lifetime of
             the scroll cursor by the duration of `page_timeout` in the scroll request.
         :param params: The values for parameters in the query.
+        :param project_routing: Specifies a subset of projects to target for the search
+            using project metadata tags in a subset of Lucene query syntax. Allowed Lucene
+            queries: the _alias tag and a single value (possibly wildcarded). Examples:
+            _alias:my-project _alias:_origin _alias:*pr* Supported in serverless only.
         :param query: The SQL query to run.
         :param request_timeout: The timeout before the request fails.
         :param runtime_mappings: One or more runtime fields for the search request. These
@@ -357,6 +362,8 @@ class SqlClient(NamespacedClient):
             __query["human"] = human
         if pretty is not None:
             __query["pretty"] = pretty
+        if project_routing is not None:
+            __query["project_routing"] = project_routing
         if not __body:
             if allow_partial_search_results is not None:
                 __body["allow_partial_search_results"] = allow_partial_search_results

elasticsearch/_sync/client/streams.py

@@ -15,6 +15,7 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
+
 import typing as t
 
 from elastic_transport import ObjectApiResponse, TextApiResponse
@@ -144,9 +145,7 @@ class StreamsClient(NamespacedClient):
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         human: t.Optional[bool] = None,
-        master_timeout: t.Optional[
-            t.Union[str, t.Literal["d", "h", "m", "micros", "ms", "nanos", "s"]]
-        ] = None,
+        master_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         pretty: t.Optional[bool] = None,
     ) -> ObjectApiResponse[t.Any]:
         """

elasticsearch/_version.py

@@ -15,5 +15,5 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
-__versionstr__ = "9.1.3"
-__es_specification_commit__ = "69144c05ec6727c4ee39aec454f7ad6a57d240fc"
+__versionstr__ = "9.2.1"
+__es_specification_commit__ = "4ab58cf013706c9104d18daafae4361cf7351a55"

elasticsearch/client.py

@@ -47,6 +47,7 @@ from ._sync.client.migration import MigrationClient as MigrationClient  # noqa:
 from ._sync.client.ml import MlClient as MlClient  # noqa: F401
 from ._sync.client.monitoring import MonitoringClient as MonitoringClient  # noqa: F401
 from ._sync.client.nodes import NodesClient as NodesClient  # noqa: F401
+from ._sync.client.project import ProjectClient as ProjectClient  # noqa: F401
 from ._sync.client.query_rules import QueryRulesClient as QueryRulesClient  # noqa: F401
 from ._sync.client.rollup import RollupClient as RollupClient  # noqa: F401
 from ._sync.client.search_application import (  # noqa: F401
@@ -106,6 +107,7 @@ __all__ = [
     "MlClient",
     "MonitoringClient",
     "NodesClient",
+    "ProjectClient",
     "RollupClient",
     "SearchApplicationClient",
     "SearchableSnapshotsClient",

elasticsearch/compat.py

@@ -15,14 +15,13 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
-import asyncio
 import inspect
 import os
 import sys
-from contextlib import asynccontextmanager, contextmanager
+from contextlib import contextmanager
 from pathlib import Path
 from threading import Thread
-from typing import Any, AsyncIterator, Callable, Coroutine, Iterator, Tuple, Type, Union
+from typing import Any, Callable, Iterator, Tuple, Type, Union
 
 string_types: Tuple[Type[str], Type[bytes]] = (str, bytes)
 
@@ -105,22 +104,10 @@ def safe_thread(
         raise captured_exception
 
 
-@asynccontextmanager
-async def safe_task(coro: Coroutine[Any, Any, Any]) -> AsyncIterator[asyncio.Task[Any]]:
-    """Run a background task within a context manager block.
-
-    The task is awaited when the block ends.
-    """
-    task = asyncio.create_task(coro)
-    yield task
-    await task
-
-
 __all__ = [
     "string_types",
     "to_str",
     "to_bytes",
     "warn_stacklevel",
     "safe_thread",
-    "safe_task",
 ]

elasticsearch/dsl/_async/document.py

@@ -125,9 +125,10 @@ class AsyncDocument(DocumentBase, metaclass=AsyncIndexMeta):
         Create an :class:`~elasticsearch.dsl.Search` instance that will search
         over this ``Document``.
         """
-        return AsyncSearch(
+        s = AsyncSearch[Self](
             using=cls._get_using(using), index=cls._default_index(index), doc_type=[cls]
         )
+        return s.source(exclude_vectors=False)
 
     @classmethod
     async def get(

elasticsearch/dsl/_sync/document.py

@@ -119,9 +119,10 @@ class Document(DocumentBase, metaclass=IndexMeta):
         Create an :class:`~elasticsearch.dsl.Search` instance that will search
         over this ``Document``.
         """
-        return Search(
+        s = Search[Self](
             using=cls._get_using(using), index=cls._default_index(index), doc_type=[cls]
         )
+        return s.source(exclude_vectors=False)
 
     @classmethod
     def get(

elasticsearch/dsl/document_base.py

@@ -34,6 +34,8 @@ from typing import (
     overload,
 )
 
+from typing_extensions import _AnnotatedAlias
+
 try:
     import annotationlib
 except ImportError:
@@ -358,6 +360,10 @@ class DocumentOptions:
                 # the field has a type annotation, so next we try to figure out
                 # what field type we can use
                 type_ = annotations[name]
+                type_metadata = []
+                if isinstance(type_, _AnnotatedAlias):
+                    type_metadata = type_.__metadata__
+                    type_ = type_.__origin__
                 skip = False
                 required = True
                 multi = False
@@ -404,6 +410,12 @@ class DocumentOptions:
                     # use best field type for the type hint provided
                     field, field_kwargs = self.type_annotation_map[type_]  # type: ignore[assignment]
 
+                # if this field does not have a right-hand value, we look in the metadata
+                # of the annotation to see if we find it there
+                for md in type_metadata:
+                    if isinstance(md, (_FieldMetadataDict, Field)):
+                        attrs[name] = md
+
                 if field:
                     field_kwargs = {
                         "multi": multi,
@@ -416,17 +428,20 @@ class DocumentOptions:
                 # this field has a right-side value, which can be field
                 # instance on its own or wrapped with mapped_field()
                 attr_value = attrs[name]
-                if isinstance(attr_value, dict):
+                if isinstance(attr_value, _FieldMetadataDict):
                     # the mapped_field() wrapper function was used so we need
                     # to look for the field instance and also record any
                     # dataclass-style defaults
+                    if attr_value.get("exclude"):
+                        # skip this field
+                        continue
                     attr_value = attrs[name].get("_field")
                     default_value = attrs[name].get("default") or attrs[name].get(
                         "default_factory"
                     )
                     if default_value:
                         field_defaults[name] = default_value
-                if attr_value:
+                if isinstance(attr_value, Field):
                     value = attr_value
                     if required is not None:
                         value._required = required
@@ -505,12 +520,19 @@ class Mapped(Generic[_FieldType]):
 M = Mapped
 
 
+class _FieldMetadataDict(dict[str, Any]):
+    """This class is used to identify metadata returned by the `mapped_field()` function."""
+
+    pass
+
+
 def mapped_field(
     field: Optional[Field] = None,
     *,
     init: bool = True,
     default: Any = None,
     default_factory: Optional[Callable[[], Any]] = None,
+    exclude: bool = False,
     **kwargs: Any,
 ) -> Any:
     """Construct a field using dataclass behaviors
@@ -520,22 +542,25 @@ def mapped_field(
     options.
 
     :param field: The instance of ``Field`` to use for this field. If not provided,
-    an instance that is appropriate for the type given to the field is used.
+        an instance that is appropriate for the type given to the field is used.
     :param init: a value of ``True`` adds this field to the constructor, and a
-    value of ``False`` omits it from it. The default is ``True``.
+        value of ``False`` omits it from it. The default is ``True``.
     :param default: a default value to use for this field when one is not provided
-    explicitly.
+        explicitly.
     :param default_factory: a callable that returns a default value for the field,
-    when one isn't provided explicitly. Only one of ``factory`` and
-    ``default_factory`` can be used.
+        when one isn't provided explicitly. Only one of ``factory`` and
+        ``default_factory`` can be used.
+    :param exclude: Set to ``True`` to exclude this field from the Elasticsearch
+        index.
     """
-    return {
-        "_field": field,
-        "init": init,
-        "default": default,
-        "default_factory": default_factory,
+    return _FieldMetadataDict(
+        _field=field,
+        init=init,
+        default=default,
+        default_factory=default_factory,
+        exclude=exclude,
         **kwargs,
-    }
+    )
 
 
 @dataclass_transform(field_specifiers=(mapped_field,))

elasticsearch/dsl/field.py

@@ -3866,6 +3866,9 @@ 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
@@ -3885,6 +3888,9 @@ 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"
         ] = DEFAULT,
@@ -3897,6 +3903,8 @@ 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: