elasticsearch 8.14.0__py3-none-any.whl → 8.15.0__py3-none-any.whl

elasticsearch/_sync/client/transform.py

@@ -36,12 +36,12 @@ class TransformClient(NamespacedClient):
         force: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Deletes an existing transform.
+        Deletes a transform.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/delete-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/delete-transform.html>`_
 
         :param transform_id: Identifier for the transform.
         :param delete_dest_index: If this value is true, the destination index is deleted
@@ -101,7 +101,7 @@ class TransformClient(NamespacedClient):
         """
         Retrieves configuration information for transforms.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/get-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/get-transform.html>`_
 
         :param transform_id: Identifier for the transform. It can be a transform identifier
             or a wildcard expression. You can get information for all transforms by using
@@ -165,12 +165,12 @@ class TransformClient(NamespacedClient):
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
         size: t.Optional[int] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
         Retrieves usage information for transforms.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/get-transform-stats.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/get-transform-stats.html>`_
 
         :param transform_id: Identifier for the transform. It can be a transform identifier
             or a wildcard expression. You can get information for all transforms by using
@@ -236,7 +236,7 @@ class TransformClient(NamespacedClient):
         dest: t.Optional[t.Mapping[str, t.Any]] = None,
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
-        frequency: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        frequency: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         human: t.Optional[bool] = None,
         latest: t.Optional[t.Mapping[str, t.Any]] = None,
         pivot: t.Optional[t.Mapping[str, t.Any]] = None,
@@ -245,13 +245,16 @@ class TransformClient(NamespacedClient):
         settings: t.Optional[t.Mapping[str, t.Any]] = None,
         source: t.Optional[t.Mapping[str, t.Any]] = None,
         sync: t.Optional[t.Mapping[str, t.Any]] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         body: t.Optional[t.Dict[str, t.Any]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Previews a transform.
+        Previews a transform. It returns a maximum of 100 results. The calculations are
+        based on all the current data in the source index. It also generates a list of
+        mappings and settings for the destination index. These values are determined
+        based on the field types of the source index and the transform aggregations.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/preview-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/preview-transform.html>`_
 
         :param transform_id: Identifier for the transform to preview. If you specify
             this path parameter, you cannot provide transform configuration details in
@@ -353,7 +356,7 @@ class TransformClient(NamespacedClient):
         description: t.Optional[str] = None,
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
-        frequency: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        frequency: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         human: t.Optional[bool] = None,
         latest: t.Optional[t.Mapping[str, t.Any]] = None,
         meta: t.Optional[t.Mapping[str, t.Any]] = None,
@@ -362,13 +365,32 @@ class TransformClient(NamespacedClient):
         retention_policy: t.Optional[t.Mapping[str, t.Any]] = None,
         settings: t.Optional[t.Mapping[str, t.Any]] = None,
         sync: t.Optional[t.Mapping[str, t.Any]] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         body: t.Optional[t.Dict[str, t.Any]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Instantiates a transform.
-
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/put-transform.html>`_
+        Creates a transform. A transform copies data from source indices, transforms
+        it, and persists it into an entity-centric destination index. You can also think
+        of the destination index as a two-dimensional tabular data structure (known as
+        a data frame). The ID for each document in the data frame is generated from a
+        hash of the entity, so there is a unique row per entity. You must choose either
+        the latest or pivot method for your transform; you cannot use both in a single
+        transform. If you choose to use the pivot method for your transform, the entities
+        are defined by the set of `group_by` fields in the pivot object. If you choose
+        to use the latest method, the entities are defined by the `unique_key` field
+        values in the latest object. You must have `create_index`, `index`, and `read`
+        privileges on the destination index and `read` and `view_index_metadata` privileges
+        on the source indices. When Elasticsearch security features are enabled, the
+        transform remembers which roles the user that created it had at the time of creation
+        and uses those same roles. If those roles do not have the required privileges
+        on the source and destination indices, the transform fails when it attempts unauthorized
+        operations. NOTE: You must use Kibana or this API to create a transform. Do not
+        add a transform directly into any `.transform-internal*` indices using the Elasticsearch
+        index API. If Elasticsearch security features are enabled, do not give users
+        any privileges on `.transform-internal*` indices. If you used transforms prior
+        to 7.5, also do not give users any privileges on `.data-frame-internal*` indices.
+
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/put-transform.html>`_
 
         :param transform_id: Identifier for the transform. This identifier can contain
             lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores.
@@ -466,9 +488,11 @@ class TransformClient(NamespacedClient):
         pretty: t.Optional[bool] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Resets an existing transform.
+        Resets a transform. Before you can reset it, you must stop it; alternatively,
+        use the `force` query parameter. If the destination index was created by the
+        transform, it is deleted.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/reset-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/reset-transform.html>`_
 
         :param transform_id: Identifier for the transform. This identifier can contain
             lowercase alphanumeric characters (a-z and 0-9), hyphens, and underscores.
@@ -511,12 +535,15 @@ class TransformClient(NamespacedClient):
         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["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Schedules now a transform.
+        Schedules now a transform. If you _schedule_now a transform, it will process
+        the new data instantly, without waiting for the configured frequency interval.
+        After _schedule_now API is called, the transform will be processed again at now
+        + frequency unless _schedule_now API is called again in the meantime.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/schedule-now-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/schedule-now-transform.html>`_
 
         :param transform_id: Identifier for the transform.
         :param timeout: Controls the time to wait for the scheduling to take place
@@ -558,12 +585,28 @@ class TransformClient(NamespacedClient):
         from_: t.Optional[str] = None,
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Starts one or more transforms.
-
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/start-transform.html>`_
+        Starts a transform. When you start a transform, it creates the destination index
+        if it does not already exist. The `number_of_shards` is set to `1` and the `auto_expand_replicas`
+        is set to `0-1`. If it is a pivot transform, it deduces the mapping definitions
+        for the destination index from the source indices and the transform aggregations.
+        If fields in the destination index are derived from scripts (as in the case of
+        `scripted_metric` or `bucket_script` aggregations), the transform uses dynamic
+        mappings unless an index template exists. If it is a latest transform, it does
+        not deduce mapping definitions; it uses dynamic mappings. To use explicit mappings,
+        create the destination index before you start the transform. Alternatively, you
+        can create an index template, though it does not affect the deduced mappings
+        in a pivot transform. When the transform starts, a series of validations occur
+        to ensure its success. If you deferred validation when you created the transform,
+        they occur when you start the transform—​with the exception of privilege checks.
+        When Elasticsearch security features are enabled, the transform remembers which
+        roles the user that created it had at the time of creation and uses those same
+        roles. If those roles do not have the required privileges on the source and destination
+        indices, the transform fails when it attempts unauthorized operations.
+
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/start-transform.html>`_
 
         :param transform_id: Identifier for the transform.
         :param from_: Restricts the set of transformed entities to those changed after
@@ -610,14 +653,14 @@ class TransformClient(NamespacedClient):
         force: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         wait_for_checkpoint: t.Optional[bool] = None,
         wait_for_completion: t.Optional[bool] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
         Stops one or more transforms.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/stop-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/stop-transform.html>`_
 
         :param transform_id: Identifier for the transform. To stop multiple transforms,
             use a comma-separated list or a wildcard expression. To stop all transforms,
@@ -696,7 +739,7 @@ class TransformClient(NamespacedClient):
         dest: t.Optional[t.Mapping[str, t.Any]] = None,
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
-        frequency: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        frequency: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         human: t.Optional[bool] = None,
         meta: t.Optional[t.Mapping[str, t.Any]] = None,
         pretty: t.Optional[bool] = None,
@@ -704,13 +747,19 @@ class TransformClient(NamespacedClient):
         settings: t.Optional[t.Mapping[str, t.Any]] = None,
         source: t.Optional[t.Mapping[str, t.Any]] = None,
         sync: t.Optional[t.Mapping[str, t.Any]] = None,
-        timeout: t.Optional[t.Union["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         body: t.Optional[t.Dict[str, t.Any]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Updates certain properties of a transform.
+        Updates certain properties of a transform. All updated properties except `description`
+        do not take effect until after the transform starts the next checkpoint, thus
+        there is data consistency in each checkpoint. To use this API, you must have
+        `read` and `view_index_metadata` privileges for the source indices. You must
+        also have `index` and `read` privileges for the destination index. When Elasticsearch
+        security features are enabled, the transform remembers which roles the user who
+        updated it had at the time of update and runs with those privileges.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/update-transform.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/update-transform.html>`_
 
         :param transform_id: Identifier for the transform.
         :param defer_validation: When true, deferrable validations are not run. This
@@ -786,12 +835,18 @@ class TransformClient(NamespacedClient):
         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["t.Literal[-1]", "t.Literal[0]", str]] = None,
+        timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Upgrades all transforms.
-
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/upgrade-transforms.html>`_
+        Upgrades all transforms. This API identifies transforms that have a legacy configuration
+        format and upgrades them to the latest version. It also cleans up the internal
+        data structures that store the transform state and checkpoints. The upgrade does
+        not affect the source and destination indices. The upgrade also does not affect
+        the roles that transforms use when Elasticsearch security features are enabled;
+        the role used to read source data and write to the destination index remains
+        unchanged.
+
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/upgrade-transforms.html>`_
 
         :param dry_run: When true, the request checks for updates but does not run them.
         :param timeout: Period to wait for a response. If no response is received before

elasticsearch/_sync/client/watcher.py

@@ -39,7 +39,7 @@ class WatcherClient(NamespacedClient):
         """
         Acknowledges a watch, manually throttling the execution of the watch's actions.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-ack-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-ack-watch.html>`_
 
         :param watch_id: Watch ID
         :param action_id: A comma-separated list of the action ids to be acked
@@ -90,7 +90,7 @@ class WatcherClient(NamespacedClient):
         """
         Activates a currently inactive watch.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-activate-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-activate-watch.html>`_
 
         :param watch_id: Watch ID
         """
@@ -130,7 +130,7 @@ class WatcherClient(NamespacedClient):
         """
         Deactivates a currently active watch.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-deactivate-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-deactivate-watch.html>`_
 
         :param watch_id: Watch ID
         """
@@ -170,7 +170,7 @@ class WatcherClient(NamespacedClient):
         """
         Removes a watch from Watcher.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-delete-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-delete-watch.html>`_
 
         :param id: Watch ID
         """
@@ -216,8 +216,10 @@ class WatcherClient(NamespacedClient):
             t.Mapping[
                 str,
                 t.Union[
-                    "t.Literal['execute', 'force_execute', 'force_simulate', 'simulate', 'skip']",
                     str,
+                    t.Literal[
+                        "execute", "force_execute", "force_simulate", "simulate", "skip"
+                    ],
                 ],
             ]
         ] = None,
@@ -235,9 +237,15 @@ class WatcherClient(NamespacedClient):
         body: t.Optional[t.Dict[str, t.Any]] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Forces the execution of a stored watch.
+        This API can be used to force execution of the watch outside of its triggering
+        logic or to simulate the watch execution for debugging purposes. For testing
+        and debugging purposes, you also have fine-grained control on how the watch runs.
+        You can execute the watch without executing all of its actions or alternatively
+        by simulating them. You can also force execution by ignoring the watch condition
+        and control whether a watch record would be written to the watch history after
+        execution.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-execute-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-execute-watch.html>`_
 
         :param id: Identifier for the watch.
         :param action_modes: Determines how to handle the watch actions as part of the
@@ -320,7 +328,7 @@ class WatcherClient(NamespacedClient):
         """
         Retrieves a watch by its ID.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-get-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-get-watch.html>`_
 
         :param id: Watch ID
         """
@@ -382,7 +390,7 @@ class WatcherClient(NamespacedClient):
         """
         Creates a new watch, or updates an existing one.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-put-watch.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-put-watch.html>`_
 
         :param id: Watch ID
         :param actions:
@@ -479,7 +487,7 @@ class WatcherClient(NamespacedClient):
         """
         Retrieves stored watches.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-query-watches.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-query-watches.html>`_
 
         :param from_: The offset from the first result to fetch. Needs to be non-negative.
         :param query: Optional, query filter watches to be returned.
@@ -549,7 +557,7 @@ class WatcherClient(NamespacedClient):
         """
         Starts Watcher if it is not already running.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-start.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-start.html>`_
         """
         __path_parts: t.Dict[str, str] = {}
         __path = "/_watcher/_start"
@@ -580,13 +588,20 @@ class WatcherClient(NamespacedClient):
             t.Union[
                 t.Sequence[
                     t.Union[
-                        "t.Literal['_all', 'current_watches', 'pending_watches', 'queued_watches']",
                         str,
+                        t.Literal[
+                            "_all",
+                            "current_watches",
+                            "pending_watches",
+                            "queued_watches",
+                        ],
                     ]
                 ],
                 t.Union[
-                    "t.Literal['_all', 'current_watches', 'pending_watches', 'queued_watches']",
                     str,
+                    t.Literal[
+                        "_all", "current_watches", "pending_watches", "queued_watches"
+                    ],
                 ],
             ]
         ] = None,
@@ -599,7 +614,7 @@ class WatcherClient(NamespacedClient):
         """
         Retrieves the current Watcher metrics.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-stats.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-stats.html>`_
 
         :param metric: Defines which additional metrics are included in the response.
         :param emit_stacktraces: Defines whether stack traces are generated for each
@@ -645,7 +660,7 @@ class WatcherClient(NamespacedClient):
         """
         Stops Watcher if it is running.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/watcher-api-stop.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/watcher-api-stop.html>`_
         """
         __path_parts: t.Dict[str, str] = {}
         __path = "/_watcher/_stop"

elasticsearch/_sync/client/xpack.py

@@ -41,9 +41,9 @@ class XPackClient(NamespacedClient):
         pretty: t.Optional[bool] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Retrieves information about the installed X-Pack features.
+        Provides general information about the installed X-Pack features.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/info-api.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/info-api.html>`_
 
         :param accept_enterprise: If this param is used it must be set to true
         :param categories: A comma-separated list of the information categories to include
@@ -81,15 +81,14 @@ class XPackClient(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["t.Literal[-1]", "t.Literal[0]", str]
-        ] = None,
+        master_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
         pretty: t.Optional[bool] = None,
     ) -> ObjectApiResponse[t.Any]:
         """
-        Retrieves usage information about the installed X-Pack features.
+        This API provides information about which features are currently enabled and
+        available under the current license and some usage statistics.
 
-        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.14/usage-api.html>`_
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.15/usage-api.html>`_
 
         :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

elasticsearch/_version.py

@@ -15,4 +15,4 @@
 #  specific language governing permissions and limitations
 #  under the License.
 
-__versionstr__ = "8.14.0"
+__versionstr__ = "8.15.0"

elasticsearch/client.py

@@ -27,6 +27,7 @@ from ._sync.client.autoscaling import (  # noqa: F401
 from ._sync.client.cat import CatClient as CatClient  # noqa: F401
 from ._sync.client.ccr import CcrClient as CcrClient  # noqa: F401
 from ._sync.client.cluster import ClusterClient as ClusterClient  # noqa: F401
+from ._sync.client.connector import ConnectorClient as ConnectorClient  # noqa: F401
 from ._sync.client.dangling_indices import (  # noqa: F401
     DanglingIndicesClient as DanglingIndicesClient,
 )
@@ -46,9 +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.query_ruleset import (  # noqa: F401
-    QueryRulesetClient as QueryRulesetClient,
-)
+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
     SearchApplicationClient as SearchApplicationClient,
@@ -86,6 +85,7 @@ __all__ = [
     "CatClient",
     "CcrClient",
     "ClusterClient",
+    "ConnectorClient",
     "DanglingIndicesClient",
     "Elasticsearch",
     "EnrichClient",

elasticsearch/helpers/vectorstore/_async/vectorstore.py

@@ -60,6 +60,7 @@ class AsyncVectorStore:
         vector_field: str = "vector_field",
         metadata_mappings: Optional[Dict[str, Any]] = None,
         user_agent: str = f"elasticsearch-py-vs/{lib_version}",
+        custom_index_settings: Optional[Dict[str, Any]] = None,
     ) -> None:
         """
         :param user_header: user agent header specific to the 3rd party integration.
@@ -72,6 +73,11 @@ class AsyncVectorStore:
             the embedding vector goes in this field.
         :param client: Elasticsearch client connection. Alternatively specify the
             Elasticsearch connection with the other es_* parameters.
+        :param custom_index_settings: A dictionary of custom settings for the index.
+            This can include configurations like the number of shards, number of replicas,
+            analysis settings, and other index-specific settings. If not provided, default
+            settings will be used. Note that if the same setting is provided by both the user
+            and the strategy, will raise an error.
         """
         # Add integration-specific usage header for tracking usage in Elastic Cloud.
         # client.options preserves existing (non-user-agent) headers.
@@ -90,6 +96,7 @@ class AsyncVectorStore:
         self.text_field = text_field
         self.vector_field = vector_field
         self.metadata_mappings = metadata_mappings
+        self.custom_index_settings = custom_index_settings
 
     async def close(self) -> None:
         return await self.client.close()
@@ -225,7 +232,7 @@ class AsyncVectorStore:
     async def search(
         self,
         *,
-        query: Optional[str],
+        query: Optional[str] = None,
         query_vector: Optional[List[float]] = None,
         k: int = 4,
         num_candidates: int = 50,
@@ -306,6 +313,16 @@ class AsyncVectorStore:
             vector_field=self.vector_field,
             num_dimensions=self.num_dimensions,
         )
+
+        if self.custom_index_settings:
+            conflicting_keys = set(self.custom_index_settings.keys()) & set(
+                settings.keys()
+            )
+            if conflicting_keys:
+                raise ValueError(f"Conflicting settings: {conflicting_keys}")
+            else:
+                settings.update(self.custom_index_settings)
+
         if self.metadata_mappings:
             metadata = mappings["properties"].get("metadata", {"properties": {}})
             for key in self.metadata_mappings.keys():
@@ -327,8 +344,9 @@ class AsyncVectorStore:
     async def max_marginal_relevance_search(
         self,
         *,
-        embedding_service: AsyncEmbeddingService,
-        query: str,
+        query: Optional[str] = None,
+        query_embedding: Optional[List[float]] = None,
+        embedding_service: Optional[AsyncEmbeddingService] = None,
         vector_field: str,
         k: int = 4,
         num_candidates: int = 20,
@@ -344,6 +362,8 @@ class AsyncVectorStore:
             among selected documents.
 
         :param query (str): Text to look up documents similar to.
+        :param query_embedding: Input embedding vector. If given, input query string is
+            ignored.
         :param k (int): Number of Documents to return. Defaults to 4.
         :param fetch_k (int): Number of Documents to fetch to pass to MMR algorithm.
         :param lambda_mult (float): Number between 0 and 1 that determines the degree
@@ -364,12 +384,22 @@ class AsyncVectorStore:
             remove_vector_query_field_from_metadata = False
 
         # Embed the query
-        query_embedding = await embedding_service.embed_query(query)
+        if query_embedding:
+            query_vector = query_embedding
+        else:
+            if not query:
+                raise ValueError("specify either query or query_embedding to search")
+            elif embedding_service:
+                query_vector = await embedding_service.embed_query(query)
+            elif self.embedding_service:
+                query_vector = await self.embedding_service.embed_query(query)
+            else:
+                raise ValueError("specify embedding_service to search with query")
 
         # Fetch the initial documents
         got_hits = await self.search(
             query=None,
-            query_vector=query_embedding,
+            query_vector=query_vector,
             k=num_candidates,
             fields=fields,
             custom_query=custom_query,
@@ -380,7 +410,7 @@ class AsyncVectorStore:
 
         # Select documents using maximal marginal relevance
         selected_indices = maximal_marginal_relevance(
-            query_embedding, got_embeddings, lambda_mult=lambda_mult, k=k
+            query_vector, got_embeddings, lambda_mult=lambda_mult, k=k
         )
         selected_hits = [got_hits[i] for i in selected_indices]