elasticsearch 8.19.0__tar.gz → 8.19.1__tar.gz

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elasticsearch
-Version: 8.19.0
+Version: 8.19.1
 Summary: Python client for Elasticsearch
 Project-URL: Documentation, https://elasticsearch-py.readthedocs.io/
 Project-URL: Homepage, https://github.com/elastic/elasticsearch-py
@@ -41,7 +41,6 @@ Requires-Dist: isort; extra == 'dev'
 Requires-Dist: jinja2; extra == 'dev'
 Requires-Dist: mapbox-vector-tile; extra == 'dev'
 Requires-Dist: mypy; extra == 'dev'
-Requires-Dist: nltk; extra == 'dev'
 Requires-Dist: nox; extra == 'dev'
 Requires-Dist: numpy; extra == 'dev'
 Requires-Dist: orjson; extra == 'dev'
@@ -55,7 +54,6 @@ Requires-Dist: pytest-mock; extra == 'dev'
 Requires-Dist: python-dateutil; extra == 'dev'
 Requires-Dist: pyyaml>=5.4; extra == 'dev'
 Requires-Dist: requests<3,>=2; extra == 'dev'
-Requires-Dist: sentence-transformers; extra == 'dev'
 Requires-Dist: simsimd; extra == 'dev'
 Requires-Dist: tqdm; extra == 'dev'
 Requires-Dist: twine; extra == 'dev'

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/__init__.py

@@ -700,6 +700,7 @@ class AsyncElasticsearch(BaseClient):
           <li>JavaScript: Check out <code>client.helpers.*</code></li>
           <li>.NET: Check out <code>BulkAllObservable</code></li>
           <li>PHP: Check out bulk indexing.</li>
+          <li>Ruby: Check out <code>Elasticsearch::Helpers::BulkHelper</code></li>
           </ul>
           <p><strong>Submitting bulk requests with cURL</strong></p>
           <p>If you're providing text file input to <code>curl</code>, you must use the <code>--data-binary</code> flag instead of plain <code>-d</code>.
@@ -1416,7 +1417,7 @@ class AsyncElasticsearch(BaseClient):
         )
 
     @_rewrite_parameters(
-        body_fields=("max_docs", "query", "slice"),
+        body_fields=("max_docs", "query", "slice", "sort"),
         parameter_aliases={"from": "from_"},
     )
     async def delete_by_query(
@@ -1460,7 +1461,12 @@ class AsyncElasticsearch(BaseClient):
         ] = None,
         slice: t.Optional[t.Mapping[str, t.Any]] = None,
         slices: t.Optional[t.Union[int, t.Union[str, t.Literal["auto"]]]] = None,
-        sort: t.Optional[t.Sequence[str]] = None,
+        sort: t.Optional[
+            t.Union[
+                t.Sequence[t.Union[str, t.Mapping[str, t.Any]]],
+                t.Union[str, t.Mapping[str, t.Any]],
+            ]
+        ] = None,
         stats: t.Optional[t.Sequence[str]] = None,
         terminate_after: t.Optional[int] = None,
         timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
@@ -1592,7 +1598,7 @@ class AsyncElasticsearch(BaseClient):
         :param slice: Slice the request manually using the provided slice ID and total
             number of slices.
         :param slices: The number of slices this task should be divided into.
-        :param sort: A comma-separated list of `<field>:<direction>` pairs.
+        :param sort: A sort object that specifies the order of deleted documents.
         :param stats: The specific `tag` of the request for logging and statistical purposes.
         :param terminate_after: The maximum number of documents to collect for each shard.
             If a query reaches this limit, Elasticsearch terminates the query early.
@@ -1682,8 +1688,6 @@ class AsyncElasticsearch(BaseClient):
             __query["search_type"] = search_type
         if slices is not None:
             __query["slices"] = slices
-        if sort is not None:
-            __query["sort"] = sort
         if stats is not None:
             __query["stats"] = stats
         if terminate_after is not None:
@@ -1703,6 +1707,8 @@ class AsyncElasticsearch(BaseClient):
                 __body["query"] = query
             if slice is not None:
                 __body["slice"] = slice
+            if sort is not None:
+                __body["sort"] = sort
         __headers = {"accept": "application/json", "content-type": "application/json"}
         return await self.perform_request(  # type: ignore[return-value]
             "POST",
@@ -6010,7 +6016,7 @@ class AsyncElasticsearch(BaseClient):
         doc: t.Optional[t.Mapping[str, t.Any]] = None,
         error_trace: t.Optional[bool] = None,
         field_statistics: t.Optional[bool] = None,
-        fields: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        fields: t.Optional[t.Sequence[str]] = None,
         filter: t.Optional[t.Mapping[str, t.Any]] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         human: t.Optional[bool] = None,

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/cat.py

@@ -47,7 +47,34 @@ class CatClient(NamespacedClient):
         ] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[
+                    t.Union[
+                        str,
+                        t.Literal[
+                            "alias",
+                            "filter",
+                            "index",
+                            "is_write_index",
+                            "routing.index",
+                            "routing.search",
+                        ],
+                    ]
+                ],
+                t.Union[
+                    str,
+                    t.Literal[
+                        "alias",
+                        "filter",
+                        "index",
+                        "is_write_index",
+                        "routing.index",
+                        "routing.search",
+                    ],
+                ],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         local: t.Optional[bool] = None,
@@ -74,7 +101,8 @@ class CatClient(NamespacedClient):
             values, such as `open,hidden`.
         :param format: Specifies the format to return the columnar data in, can be set
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
-        :param h: List of columns to appear in the response. Supports simple wildcards.
+        :param h: A comma-separated list of columns names to display. It supports simple
+            wildcards.
         :param help: When set to `true` will output available columns. This option can't
             be combined with any other query string option.
         :param local: If `true`, the request computes the list of selected nodes from
@@ -137,7 +165,48 @@ class CatClient(NamespacedClient):
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[
+                    t.Union[
+                        str,
+                        t.Literal[
+                            "disk.avail",
+                            "disk.indices",
+                            "disk.indices.forecast",
+                            "disk.percent",
+                            "disk.total",
+                            "disk.used",
+                            "host",
+                            "ip",
+                            "node",
+                            "node.role",
+                            "shards",
+                            "shards.undesired",
+                            "write_load.forecast",
+                        ],
+                    ]
+                ],
+                t.Union[
+                    str,
+                    t.Literal[
+                        "disk.avail",
+                        "disk.indices",
+                        "disk.indices.forecast",
+                        "disk.percent",
+                        "disk.total",
+                        "disk.used",
+                        "host",
+                        "ip",
+                        "node",
+                        "node.role",
+                        "shards",
+                        "shards.undesired",
+                        "write_load.forecast",
+                    ],
+                ],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         local: t.Optional[bool] = None,
@@ -161,7 +230,8 @@ class CatClient(NamespacedClient):
         :param bytes: The unit used to display byte values.
         :param format: Specifies the format to return the columnar data in, can be set
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
-        :param h: List of columns to appear in the response. Supports simple wildcards.
+        :param h: A comma-separated list of columns names to display. It supports simple
+            wildcards.
         :param help: When set to `true` will output available columns. This option can't
             be combined with any other query string option.
         :param local: If `true`, the request computes the list of selected nodes from
@@ -224,7 +294,36 @@ class CatClient(NamespacedClient):
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[
+                    t.Union[
+                        str,
+                        t.Literal[
+                            "alias_count",
+                            "included_in",
+                            "mapping_count",
+                            "metadata_count",
+                            "name",
+                            "settings_count",
+                            "version",
+                        ],
+                    ]
+                ],
+                t.Union[
+                    str,
+                    t.Literal[
+                        "alias_count",
+                        "included_in",
+                        "mapping_count",
+                        "metadata_count",
+                        "name",
+                        "settings_count",
+                        "version",
+                    ],
+                ],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         local: t.Optional[bool] = None,
@@ -249,7 +348,8 @@ class CatClient(NamespacedClient):
             If it is omitted, all component templates are returned.
         :param format: Specifies the format to return the columnar data in, can be set
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
-        :param h: List of columns to appear in the response. Supports simple wildcards.
+        :param h: A comma-separated list of columns names to display. It supports simple
+            wildcards.
         :param help: When set to `true` will output available columns. This option can't
             be combined with any other query string option.
         :param local: If `true`, the request computes the list of selected nodes from
@@ -310,7 +410,12 @@ class CatClient(NamespacedClient):
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[t.Union[str, t.Literal["count", "epoch", "timestamp"]]],
+                t.Union[str, t.Literal["count", "epoch", "timestamp"]],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
@@ -334,7 +439,8 @@ class CatClient(NamespacedClient):
             and indices, omit this parameter or use `*` or `_all`.
         :param format: Specifies the format to return the columnar data in, can be set
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
-        :param h: List of columns to appear in the response. Supports simple wildcards.
+        :param h: A comma-separated list of columns names to display. It supports simple
+            wildcards.
         :param help: When set to `true` will output available columns. This option can't
             be combined with any other query string option.
         :param s: List of columns that determine how the table should be sorted. Sorting
@@ -389,7 +495,14 @@ class CatClient(NamespacedClient):
         error_trace: t.Optional[bool] = None,
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[
+                    t.Union[str, t.Literal["field", "host", "id", "ip", "node", "size"]]
+                ],
+                t.Union[str, t.Literal["field", "host", "id", "ip", "node", "size"]],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         pretty: t.Optional[bool] = None,
@@ -412,7 +525,8 @@ class CatClient(NamespacedClient):
         :param bytes: The unit used to display byte values.
         :param format: Specifies the format to return the columnar data in, can be set
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
-        :param h: List of columns to appear in the response. Supports simple wildcards.
+        :param h: A comma-separated list of columns names to display. It supports simple
+            wildcards.
         :param help: When set to `true` will output available columns. This option can't
             be combined with any other query string option.
         :param s: List of columns that determine how the table should be sorted. Sorting

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/cluster.py

@@ -373,8 +373,13 @@ class ClusterClient(NamespacedClient):
         `<https://www.elastic.co/guide/en/elasticsearch/reference/8.19/cluster-get-settings.html>`_
 
         :param flat_settings: If `true`, returns settings in flat format.
-        :param include_defaults: If `true`, returns default cluster settings from the
-            local node.
+        :param include_defaults: If `true`, also returns default values for all other
+            cluster settings, reflecting the values in the `elasticsearch.yml` file of
+            one of the nodes in the cluster. If the nodes in your cluster do not all
+            have the same values in their `elasticsearch.yml` config files then the values
+            returned by this API may vary from invocation to invocation and may not reflect
+            the values that Elasticsearch uses in all situations. Use the `GET _nodes/settings`
+            API to fetch the settings for each individual node in your cluster.
         :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
             returns an error.

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/esql.py

@@ -22,6 +22,9 @@ from elastic_transport import ObjectApiResponse
 from ._base import NamespacedClient
 from .utils import SKIP_IN_PATH, _quote, _rewrite_parameters
 
+if t.TYPE_CHECKING:
+    from elasticsearch.esql import ESQLBase
+
 
 class EsqlClient(NamespacedClient):
 
@@ -44,7 +47,7 @@ class EsqlClient(NamespacedClient):
     async def async_query(
         self,
         *,
-        query: t.Optional[str] = None,
+        query: t.Optional[t.Union[str, "ESQLBase"]] = None,
         allow_partial_results: t.Optional[bool] = None,
         columnar: t.Optional[bool] = None,
         delimiter: t.Optional[str] = None,
@@ -107,7 +110,12 @@ class EsqlClient(NamespacedClient):
             which has the name of all the columns.
         :param filter: Specify a Query DSL query in the filter parameter to filter the
             set of documents that an ES|QL query runs on.
-        :param format: A short version of the Accept header, for example `json` or `yaml`.
+        :param format: A short version of the Accept header, e.g. json, yaml. `csv`,
+            `tsv`, and `txt` formats will return results in a tabular format, excluding
+            other metadata fields from the response. For async requests, nothing will
+            be returned if the async query doesn't finish within the timeout. The query
+            ID and running status are available in the `X-Elasticsearch-Async-Id` and
+            `X-Elasticsearch-Async-Is-Running` HTTP headers of the response, respectively.
         :param include_ccs_metadata: When set to `true` and performing a cross-cluster
             query, the response will include an extra `_clusters` object with information
             about the clusters that participated in the search along with info such as
@@ -161,7 +169,7 @@ class EsqlClient(NamespacedClient):
             __query["pretty"] = pretty
         if not __body:
             if query is not None:
-                __body["query"] = query
+                __body["query"] = str(query)
             if columnar is not None:
                 __body["columnar"] = columnar
             if filter is not None:
@@ -399,7 +407,7 @@ class EsqlClient(NamespacedClient):
     async def query(
         self,
         *,
-        query: t.Optional[str] = None,
+        query: t.Optional[t.Union[str, "ESQLBase"]] = None,
         allow_partial_results: t.Optional[bool] = None,
         columnar: t.Optional[bool] = None,
         delimiter: t.Optional[str] = None,
@@ -456,7 +464,9 @@ class EsqlClient(NamespacedClient):
             `all_columns` which has the name of all columns.
         :param filter: Specify a Query DSL query in the filter parameter to filter the
             set of documents that an ES|QL query runs on.
-        :param format: A short version of the Accept header, e.g. json, yaml.
+        :param format: A short version of the Accept header, e.g. json, yaml. `csv`,
+            `tsv`, and `txt` formats will return results in a tabular format, excluding
+            other metadata fields from the response.
         :param include_ccs_metadata: When set to `true` and performing a cross-cluster
             query, the response will include an extra `_clusters` object with information
             about the clusters that participated in the search along with info such as
@@ -496,7 +506,7 @@ class EsqlClient(NamespacedClient):
             __query["pretty"] = pretty
         if not __body:
             if query is not None:
-                __body["query"] = query
+                __body["query"] = str(query)
             if columnar is not None:
                 __body["columnar"] = columnar
             if filter is not None:

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/indices.py

@@ -4581,7 +4581,7 @@ class IndicesClient(NamespacedClient):
         .. raw:: html
 
           <p>Roll over to a new index.
-          TIP: It is recommended to use the index lifecycle rollover action to automate rollovers.</p>
+          TIP: We recommend using the index lifecycle rollover action to automate rollovers. However, Serverless does not support Index Lifecycle Management (ILM), so don't use this approach in the Serverless context.</p>
           <p>The rollover API creates a new index for a data stream or index alias.
           The API behavior depends on the rollover target.</p>
           <p><strong>Roll over a data stream</strong></p>

{elasticsearch-8.19.0 → elasticsearch-8.19.1}/elasticsearch/_async/client/inference.py

@@ -391,21 +391,23 @@ class InferenceClient(NamespacedClient):
           <ul>
           <li>AlibabaCloud AI Search (<code>completion</code>, <code>rerank</code>, <code>sparse_embedding</code>, <code>text_embedding</code>)</li>
           <li>Amazon Bedrock (<code>completion</code>, <code>text_embedding</code>)</li>
+          <li>Amazon SageMaker (<code>chat_completion</code>, <code>completion</code>, <code>rerank</code>, <code>sparse_embedding</code>, <code>text_embedding</code>)</li>
           <li>Anthropic (<code>completion</code>)</li>
           <li>Azure AI Studio (<code>completion</code>, <code>text_embedding</code>)</li>
           <li>Azure OpenAI (<code>completion</code>, <code>text_embedding</code>)</li>
           <li>Cohere (<code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
-          <li>DeepSeek (<code>completion</code>, <code>chat_completion</code>)</li>
+          <li>DeepSeek (<code>chat_completion</code>, <code>completion</code>)</li>
           <li>Elasticsearch (<code>rerank</code>, <code>sparse_embedding</code>, <code>text_embedding</code> - this service is for built-in models and models uploaded through Eland)</li>
           <li>ELSER (<code>sparse_embedding</code>)</li>
           <li>Google AI Studio (<code>completion</code>, <code>text_embedding</code>)</li>
-          <li>Google Vertex AI (<code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>Google Vertex AI (<code>chat_completion</code>, <code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
           <li>Hugging Face (<code>chat_completion</code>, <code>completion</code>, <code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>JinaAI (<code>rerank</code>, <code>text_embedding</code>)</li>
+          <li>Llama (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
           <li>Mistral (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
           <li>OpenAI (<code>chat_completion</code>, <code>completion</code>, <code>text_embedding</code>)</li>
-          <li>VoyageAI (<code>text_embedding</code>, <code>rerank</code>)</li>
+          <li>VoyageAI (<code>rerank</code>, <code>text_embedding</code>)</li>
           <li>Watsonx inference integration (<code>text_embedding</code>)</li>
-          <li>JinaAI (<code>text_embedding</code>, <code>rerank</code>)</li>
           </ul>
 
 
@@ -659,6 +661,112 @@ class InferenceClient(NamespacedClient):
             path_parts=__path_parts,
         )
 
+    @_rewrite_parameters(
+        body_fields=(
+            "service",
+            "service_settings",
+            "chunking_settings",
+            "task_settings",
+        ),
+    )
+    async def put_amazonsagemaker(
+        self,
+        *,
+        task_type: t.Union[
+            str,
+            t.Literal[
+                "chat_completion",
+                "completion",
+                "rerank",
+                "sparse_embedding",
+                "text_embedding",
+            ],
+        ],
+        amazonsagemaker_inference_id: str,
+        service: t.Optional[t.Union[str, t.Literal["amazon_sagemaker"]]] = None,
+        service_settings: t.Optional[t.Mapping[str, t.Any]] = None,
+        chunking_settings: 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,
+        human: t.Optional[bool] = None,
+        pretty: t.Optional[bool] = None,
+        task_settings: t.Optional[t.Mapping[str, t.Any]] = 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]:
+        """
+        .. raw:: html
+
+          <p>Create an Amazon SageMaker inference endpoint.</p>
+          <p>Create an inference endpoint to perform an inference task with the <code>amazon_sagemaker</code> service.</p>
+
+
+        `<https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-amazonsagemaker>`_
+
+        :param task_type: The type of the inference task that the model will perform.
+        :param amazonsagemaker_inference_id: The unique identifier of the inference endpoint.
+        :param service: The type of service supported for the specified task type. In
+            this case, `amazon_sagemaker`.
+        :param service_settings: Settings used to install the inference model. These
+            settings are specific to the `amazon_sagemaker` service and `service_settings.api`
+            you specified.
+        :param chunking_settings: The chunking configuration object.
+        :param task_settings: Settings to configure the inference task. These settings
+            are specific to the task type and `service_settings.api` you specified.
+        :param timeout: Specifies the amount of time to wait for the inference endpoint
+            to be created.
+        """
+        if task_type in SKIP_IN_PATH:
+            raise ValueError("Empty value passed for parameter 'task_type'")
+        if amazonsagemaker_inference_id in SKIP_IN_PATH:
+            raise ValueError(
+                "Empty value passed for parameter 'amazonsagemaker_inference_id'"
+            )
+        if service is None and body is None:
+            raise ValueError("Empty value passed for parameter 'service'")
+        if service_settings is None and body is None:
+            raise ValueError("Empty value passed for parameter 'service_settings'")
+        __path_parts: t.Dict[str, str] = {
+            "task_type": _quote(task_type),
+            "amazonsagemaker_inference_id": _quote(amazonsagemaker_inference_id),
+        }
+        __path = f'/_inference/{__path_parts["task_type"]}/{__path_parts["amazonsagemaker_inference_id"]}'
+        __query: t.Dict[str, t.Any] = {}
+        __body: t.Dict[str, t.Any] = body if body is not None else {}
+        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
+        if timeout is not None:
+            __query["timeout"] = timeout
+        if not __body:
+            if service is not None:
+                __body["service"] = service
+            if service_settings is not None:
+                __body["service_settings"] = service_settings
+            if chunking_settings is not None:
+                __body["chunking_settings"] = chunking_settings
+            if task_settings is not None:
+                __body["task_settings"] = task_settings
+        if not __body:
+            __body = None  # type: ignore[assignment]
+        __headers = {"accept": "application/json"}
+        if __body is not None:
+            __headers["content-type"] = "application/json"
+        return await self.perform_request(  # type: ignore[return-value]
+            "PUT",
+            __path,
+            params=__query,
+            headers=__headers,
+            body=__body,
+            endpoint_id="inference.put_amazonsagemaker",
+            path_parts=__path_parts,
+        )
+
     @_rewrite_parameters(
         body_fields=(
             "service",