elasticsearch 9.0.1__tar.gz → 9.0.2__tar.gz

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: elasticsearch
-Version: 9.0.1
+Version: 9.0.2
 Summary: Python client for Elasticsearch
 Project-URL: Documentation, https://elasticsearch-py.readthedocs.io/
 Project-URL: Homepage, https://github.com/elastic/elasticsearch-py
@@ -10,9 +10,7 @@ Author-email: Elastic Client Library Maintainers <client-libs@elastic.co>
 Maintainer-email: Elastic Client Library Maintainers <client-libs@elastic.co>
 License-Expression: Apache-2.0
 License-File: LICENSE
-License-File: LICENSE.txt
 License-File: NOTICE
-License-File: NOTICE.txt
 Keywords: REST,client,elastic,elasticsearch,index,kibana,mapping,search
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/docs/sphinx/index.rst

@@ -1,6 +1,12 @@
 Python Elasticsearch Client
 ===========================
 
+Welcome to the API documentation of the official Python client for Elasticsearch!
+The goal of this client is to provide common ground for all Elasticsearch-related
+code in Python; because of this it tries to be opinion-free and very extendable.
+
+High-level documentation for this client is `also available <https://www.elastic.co/docs/reference/elasticsearch/clients/python>`_.
+
 .. toctree::
    :maxdepth: 2 
 

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/elasticsearch/_async/client/__init__.py

@@ -4652,11 +4652,11 @@ class AsyncElasticsearch(BaseClient):
             of the specified nodes are available, select shards from any available node
             using the default method. * `_prefer_nodes:<node-id>,<node-id>` to if possible,
             run the search on the specified nodes IDs. If not, select shards using the
-            default method. `_shards:<shard>,<shard>` to run the search only on the specified
-            shards. You can combine this value with other `preference` values. However,
-            the `_shards` value must come first. For example: `_shards:2,3|_local`. `<custom-string>`
-            (any string that does not start with `_`) to route searches with the same
-            `<custom-string>` to the same shards in the same order.
+            default method. * `_shards:<shard>,<shard>` to run the search only on the
+            specified shards. You can combine this value with other `preference` values.
+            However, the `_shards` value must come first. For example: `_shards:2,3|_local`.
+            * `<custom-string>` (any string that does not start with `_`) to route searches
+            with the same `<custom-string>` to the same shards in the same order.
         :param profile: Set to `true` to return detailed timing information about the
             execution of individual components in a search request. NOTE: This is a debugging
             tool and adds significant overhead to search execution.

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/elasticsearch/_async/client/cat.py

@@ -1767,7 +1767,200 @@ class CatClient(NamespacedClient):
         filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
         format: t.Optional[str] = None,
         full_id: t.Optional[t.Union[bool, str]] = None,
-        h: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        h: t.Optional[
+            t.Union[
+                t.Sequence[
+                    t.Union[
+                        str,
+                        t.Literal[
+                            "build",
+                            "completion.size",
+                            "cpu",
+                            "disk.avail",
+                            "disk.total",
+                            "disk.used",
+                            "disk.used_percent",
+                            "fielddata.evictions",
+                            "fielddata.memory_size",
+                            "file_desc.current",
+                            "file_desc.max",
+                            "file_desc.percent",
+                            "flush.total",
+                            "flush.total_time",
+                            "get.current",
+                            "get.exists_time",
+                            "get.exists_total",
+                            "get.missing_time",
+                            "get.missing_total",
+                            "get.time",
+                            "get.total",
+                            "heap.current",
+                            "heap.max",
+                            "heap.percent",
+                            "http_address",
+                            "id",
+                            "indexing.delete_current",
+                            "indexing.delete_time",
+                            "indexing.delete_total",
+                            "indexing.index_current",
+                            "indexing.index_failed",
+                            "indexing.index_failed_due_to_version_conflict",
+                            "indexing.index_time",
+                            "indexing.index_total",
+                            "ip",
+                            "jdk",
+                            "load_15m",
+                            "load_1m",
+                            "load_5m",
+                            "mappings.total_count",
+                            "mappings.total_estimated_overhead_in_bytes",
+                            "master",
+                            "merges.current",
+                            "merges.current_docs",
+                            "merges.current_size",
+                            "merges.total",
+                            "merges.total_docs",
+                            "merges.total_size",
+                            "merges.total_time",
+                            "name",
+                            "node.role",
+                            "pid",
+                            "port",
+                            "query_cache.evictions",
+                            "query_cache.hit_count",
+                            "query_cache.memory_size",
+                            "query_cache.miss_count",
+                            "ram.current",
+                            "ram.max",
+                            "ram.percent",
+                            "refresh.time",
+                            "refresh.total",
+                            "request_cache.evictions",
+                            "request_cache.hit_count",
+                            "request_cache.memory_size",
+                            "request_cache.miss_count",
+                            "script.cache_evictions",
+                            "script.compilations",
+                            "search.fetch_current",
+                            "search.fetch_time",
+                            "search.fetch_total",
+                            "search.open_contexts",
+                            "search.query_current",
+                            "search.query_time",
+                            "search.query_total",
+                            "search.scroll_current",
+                            "search.scroll_time",
+                            "search.scroll_total",
+                            "segments.count",
+                            "segments.fixed_bitset_memory",
+                            "segments.index_writer_memory",
+                            "segments.memory",
+                            "segments.version_map_memory",
+                            "shard_stats.total_count",
+                            "suggest.current",
+                            "suggest.time",
+                            "suggest.total",
+                            "uptime",
+                            "version",
+                        ],
+                    ]
+                ],
+                t.Union[
+                    str,
+                    t.Literal[
+                        "build",
+                        "completion.size",
+                        "cpu",
+                        "disk.avail",
+                        "disk.total",
+                        "disk.used",
+                        "disk.used_percent",
+                        "fielddata.evictions",
+                        "fielddata.memory_size",
+                        "file_desc.current",
+                        "file_desc.max",
+                        "file_desc.percent",
+                        "flush.total",
+                        "flush.total_time",
+                        "get.current",
+                        "get.exists_time",
+                        "get.exists_total",
+                        "get.missing_time",
+                        "get.missing_total",
+                        "get.time",
+                        "get.total",
+                        "heap.current",
+                        "heap.max",
+                        "heap.percent",
+                        "http_address",
+                        "id",
+                        "indexing.delete_current",
+                        "indexing.delete_time",
+                        "indexing.delete_total",
+                        "indexing.index_current",
+                        "indexing.index_failed",
+                        "indexing.index_failed_due_to_version_conflict",
+                        "indexing.index_time",
+                        "indexing.index_total",
+                        "ip",
+                        "jdk",
+                        "load_15m",
+                        "load_1m",
+                        "load_5m",
+                        "mappings.total_count",
+                        "mappings.total_estimated_overhead_in_bytes",
+                        "master",
+                        "merges.current",
+                        "merges.current_docs",
+                        "merges.current_size",
+                        "merges.total",
+                        "merges.total_docs",
+                        "merges.total_size",
+                        "merges.total_time",
+                        "name",
+                        "node.role",
+                        "pid",
+                        "port",
+                        "query_cache.evictions",
+                        "query_cache.hit_count",
+                        "query_cache.memory_size",
+                        "query_cache.miss_count",
+                        "ram.current",
+                        "ram.max",
+                        "ram.percent",
+                        "refresh.time",
+                        "refresh.total",
+                        "request_cache.evictions",
+                        "request_cache.hit_count",
+                        "request_cache.memory_size",
+                        "request_cache.miss_count",
+                        "script.cache_evictions",
+                        "script.compilations",
+                        "search.fetch_current",
+                        "search.fetch_time",
+                        "search.fetch_total",
+                        "search.open_contexts",
+                        "search.query_current",
+                        "search.query_time",
+                        "search.query_total",
+                        "search.scroll_current",
+                        "search.scroll_time",
+                        "search.scroll_total",
+                        "segments.count",
+                        "segments.fixed_bitset_memory",
+                        "segments.index_writer_memory",
+                        "segments.memory",
+                        "segments.version_map_memory",
+                        "shard_stats.total_count",
+                        "suggest.current",
+                        "suggest.time",
+                        "suggest.total",
+                        "uptime",
+                        "version",
+                    ],
+                ],
+            ]
+        ] = None,
         help: t.Optional[bool] = None,
         human: t.Optional[bool] = None,
         include_unloaded_segments: t.Optional[bool] = None,
@@ -1794,16 +1987,17 @@ class CatClient(NamespacedClient):
             to `text`, `json`, `cbor`, `yaml`, or `smile`.
         :param full_id: If `true`, return the full node ID. If `false`, return the shortened
             node ID.
-        :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 include_unloaded_segments: If true, the response includes information
             from segments that are not loaded into memory.
-        :param master_timeout: Period to wait for a connection to the master node.
-        :param s: List of columns that determine how the table should be sorted. Sorting
-            defaults to ascending and can be changed by setting `:asc` or `:desc` as
-            a suffix to the column name.
-        :param time: Unit used to display time values.
+        :param master_timeout: The period to wait for a connection to the master node.
+        :param s: A comma-separated list of column names or aliases that determines the
+            sort order. Sorting defaults to ascending and can be changed by setting `:asc`
+            or `:desc` as a suffix to the column name.
+        :param time: The unit used to display time values.
         :param v: When set to `true` will enable verbose output.
         """
         __path_parts: t.Dict[str, str] = {}

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/elasticsearch/_async/client/indices.py

@@ -656,7 +656,15 @@ class IndicesClient(NamespacedClient):
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-indices-create>`_
 
-        :param index: Name of the index you wish to create.
+        :param index: Name of the index you wish to create. Index names must meet the
+            following criteria: * Lowercase only * Cannot include `\\`, `/`, `*`, `?`,
+            `"`, `<`, `>`, `|`, ` ` (space character), `,`, or `#` * Indices prior to
+            7.0 could contain a colon (`:`), but that has been deprecated and will not
+            be supported in later versions * Cannot start with `-`, `_`, or `+` * Cannot
+            be `.` or `..` * Cannot be longer than 255 bytes (note thtat it is bytes,
+            so multi-byte characters will reach the limit faster) * Names starting with
+            `.` are deprecated, except for hidden indices and internal indices managed
+            by plugins
         :param aliases: Aliases for the index.
         :param mappings: Mapping for fields in the index. If specified, this mapping
             can include: - Field names - Field data types - Mapping parameters
@@ -1246,7 +1254,8 @@ class IndicesClient(NamespacedClient):
         """
         .. raw:: html
 
-          <p>Delete a legacy index template.</p>
+          <p>Delete a legacy index template.
+          IMPORTANT: This documentation is about legacy index templates, which are deprecated and will be replaced by the composable templates introduced in Elasticsearch 7.8.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-indices-delete-template>`_
@@ -2880,7 +2889,7 @@ class IndicesClient(NamespacedClient):
         """
         .. raw:: html
 
-          <p>Get index templates.
+          <p>Get legacy index templates.
           Get information about one or more index templates.</p>
           <p>IMPORTANT: This documentation is about legacy index templates, which are deprecated and will be replaced by the composable templates introduced in Elasticsearch 7.8.</p>
 
@@ -3973,7 +3982,7 @@ class IndicesClient(NamespacedClient):
         """
         .. raw:: html
 
-          <p>Create or update an index template.
+          <p>Create or update a legacy index template.
           Index templates define settings, mappings, and aliases that can be applied automatically to new indices.
           Elasticsearch applies templates to new indices based on an index pattern that matches the index name.</p>
           <p>IMPORTANT: This documentation is about legacy index templates, which are deprecated and will be replaced by the composable templates introduced in Elasticsearch 7.8.</p>

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/elasticsearch/_async/client/inference.py

@@ -370,12 +370,7 @@ class InferenceClient(NamespacedClient):
         """
         .. raw:: html
 
-          <p>Create an inference endpoint.
-          When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
+          <p>Create an inference endpoint.</p>
           <p>IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.
           For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.
           However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.</p>
@@ -458,11 +453,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create an AlibabaCloud AI Search inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>alibabacloud-ai-search</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-alibabacloud>`_
@@ -558,11 +548,6 @@ class InferenceClient(NamespacedClient):
           <p>info
           You need to provide the access and secret keys only once, during the inference model creation. The get inference API does not retrieve your access or secret keys. After creating the inference model, you cannot change the associated key pairs. If you want to use a different access and secret key pair, delete the inference model and recreate it with the same name and the updated keys.</p>
           </blockquote>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-amazonbedrock>`_
@@ -654,11 +639,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create an Anthropic inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>anthropic</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-anthropic>`_
@@ -751,11 +731,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create an Azure AI studio inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>azureaistudio</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-azureaistudio>`_
@@ -853,11 +828,6 @@ class InferenceClient(NamespacedClient):
           <li><a href="https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#gpt-35">GPT-3.5</a></li>
           </ul>
           <p>The list of embeddings models that you can choose from in your deployment can be found in the <a href="https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#embeddings">Azure models documentation</a>.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-azureopenai>`_
@@ -951,11 +921,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create a Cohere inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>cohere</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-cohere>`_
@@ -1239,11 +1204,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create an Google AI Studio inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>googleaistudio</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-googleaistudio>`_
@@ -1331,11 +1291,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create a Google Vertex AI inference endpoint.</p>
           <p>Create an inference endpoint to perform an inference task with the <code>googlevertexai</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-googlevertexai>`_
@@ -1434,11 +1389,6 @@ class InferenceClient(NamespacedClient):
           <li><code>multilingual-e5-base</code></li>
           <li><code>multilingual-e5-small</code></li>
           </ul>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-hugging-face>`_
@@ -1528,11 +1478,6 @@ class InferenceClient(NamespacedClient):
           <p>Create an inference endpoint to perform an inference task with the <code>jinaai</code> service.</p>
           <p>To review the available <code>rerank</code> models, refer to <a href="https://jina.ai/reranker">https://jina.ai/reranker</a>.
           To review the available <code>text_embedding</code> models, refer to the <a href="https://jina.ai/embeddings/">https://jina.ai/embeddings/</a>.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-jinaai>`_
@@ -1616,11 +1561,6 @@ class InferenceClient(NamespacedClient):
 
           <p>Create a Mistral inference endpoint.</p>
           <p>Creates an inference endpoint to perform an inference task with the <code>mistral</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-mistral>`_
@@ -1708,12 +1648,7 @@ class InferenceClient(NamespacedClient):
         .. raw:: html
 
           <p>Create an OpenAI inference endpoint.</p>
-          <p>Create an inference endpoint to perform an inference task with the <code>openai</code> service.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
+          <p>Create an inference endpoint to perform an inference task with the <code>openai</code> service or <code>openai</code> compatible APIs.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-openai>`_
@@ -1890,11 +1825,6 @@ class InferenceClient(NamespacedClient):
           <p>Create an inference endpoint to perform an inference task with the <code>watsonxai</code> service.
           You need an IBM Cloud Databases for Elasticsearch deployment to use the <code>watsonxai</code> inference service.
           You can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform.</p>
-          <p>When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
-          After creating the endpoint, wait for the model deployment to complete before using it.
-          To verify the deployment status, use the get trained model statistics API.
-          Look for <code>&quot;state&quot;: &quot;fully_allocated&quot;</code> in the response and ensure that the <code>&quot;allocation_count&quot;</code> matches the <code>&quot;target_allocation_count&quot;</code>.
-          Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.</p>
 
 
         `<https://www.elastic.co/docs/api/doc/elasticsearch/v9/operation/operation-inference-put-watsonx>`_

{elasticsearch-9.0.1 → elasticsearch-9.0.2}/elasticsearch/_sync/client/__init__.py

@@ -4650,11 +4650,11 @@ class Elasticsearch(BaseClient):
             of the specified nodes are available, select shards from any available node
             using the default method. * `_prefer_nodes:<node-id>,<node-id>` to if possible,
             run the search on the specified nodes IDs. If not, select shards using the
-            default method. `_shards:<shard>,<shard>` to run the search only on the specified
-            shards. You can combine this value with other `preference` values. However,
-            the `_shards` value must come first. For example: `_shards:2,3|_local`. `<custom-string>`
-            (any string that does not start with `_`) to route searches with the same
-            `<custom-string>` to the same shards in the same order.
+            default method. * `_shards:<shard>,<shard>` to run the search only on the
+            specified shards. You can combine this value with other `preference` values.
+            However, the `_shards` value must come first. For example: `_shards:2,3|_local`.
+            * `<custom-string>` (any string that does not start with `_`) to route searches
+            with the same `<custom-string>` to the same shards in the same order.
         :param profile: Set to `true` to return detailed timing information about the
             execution of individual components in a search request. NOTE: This is a debugging
             tool and adds significant overhead to search execution.