elastic · pquentin · May 24, 2024 · May 24, 2024
diff --git a/docs/examples/00fea15cbca83be9d5f1a024ff2ec708.asciidoc b/docs/examples/00fea15cbca83be9d5f1a024ff2ec708.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:381
+// inference/put-inference.asciidoc:452
 
 [source, python]
 ----

diff --git a/docs/examples/10c3fe2265bb34964bd1005f9da66773.asciidoc b/docs/examples/10c3fe2265bb34964bd1005f9da66773.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:488
+// inference/put-inference.asciidoc:559
 
 [source, python]
 ----

diff --git a/docs/examples/1dadb7efe27b6c0c231eb6535e413bd9.asciidoc b/docs/examples/1dadb7efe27b6c0c231eb6535e413bd9.asciidoc
@@ -0,0 +1,19 @@
+// inference/put-inference.asciidoc:671
+
+[source, python]
+----
+resp = client.inference.put_model(
+    task_type="text_embedding",
+    inference_id="azure_ai_studio_embeddings",
+    body={
+        "service": "azureaistudio",
+        "service_settings": {
+            "api_key": "<api_key>",
+            "target": "<target_uri>",
+            "provider": "<model_provider>",
+            "endpoint_type": "<endpoint_type>",
+        },
+    },
+)
+print(resp)
+----
diff --git a/docs/examples/3541d4a85e27b2c3896a7a7ee98b4b37.asciidoc b/docs/examples/3541d4a85e27b2c3896a7a7ee98b4b37.asciidoc
@@ -1,4 +1,4 @@
-// health/health.asciidoc:478
+// health/health.asciidoc:481
 
 [source, python]
 ----

diff --git a/docs/examples/36b86b97feedcf5632824eefc251d6ed.asciidoc b/docs/examples/36b86b97feedcf5632824eefc251d6ed.asciidoc
diff --git a/docs/examples/4ca15672fc5ab1d80a127d086b6d2837.asciidoc b/docs/examples/4ca15672fc5ab1d80a127d086b6d2837.asciidoc
@@ -1,4 +1,4 @@
-// cluster/allocation-explain.asciidoc:342
+// cluster/allocation-explain.asciidoc:344
 
 [source, python]
 ----

diff --git a/docs/examples/5553cf7a02c22f616cd994747f2dd5a5.asciidoc b/docs/examples/5553cf7a02c22f616cd994747f2dd5a5.asciidoc
@@ -1,4 +1,4 @@
-// mapping/types/nested.asciidoc:58
+// mapping/types/nested.asciidoc:60
 
 [source, python]
 ----

diff --git a/docs/examples/59d736a4d064ed2013c7ead8e32e0998.asciidoc b/docs/examples/59d736a4d064ed2013c7ead8e32e0998.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:529
+// inference/put-inference.asciidoc:600
 
 [source, python]
 ----

diff --git a/docs/examples/6cd083045bf06e80b83889a939a18451.asciidoc b/docs/examples/6cd083045bf06e80b83889a939a18451.asciidoc
@@ -1,4 +1,4 @@
-// mapping/types/nested.asciidoc:85
+// mapping/types/nested.asciidoc:87
 
 [source, python]
 ----

diff --git a/docs/examples/6ddd4e657efbf45def430a6419825796.asciidoc b/docs/examples/6ddd4e657efbf45def430a6419825796.asciidoc
@@ -0,0 +1,19 @@
+// inference/put-inference.asciidoc:689
+
+[source, python]
+----
+resp = client.inference.put_model(
+    task_type="completion",
+    inference_id="azure_ai_studio_completion",
+    body={
+        "service": "azureaistudio",
+        "service_settings": {
+            "api_key": "<api_key>",
+            "target": "<target_uri>",
+            "provider": "<model_provider>",
+            "endpoint_type": "<endpoint_type>",
+        },
+    },
+)
+print(resp)
+----
diff --git a/docs/examples/70cc66bf4054ebf0ad4955cb99d9ab80.asciidoc b/docs/examples/70cc66bf4054ebf0ad4955cb99d9ab80.asciidoc
@@ -1,4 +1,4 @@
-// ml/trained-models/apis/update-trained-model-deployment.asciidoc:55
+// ml/trained-models/apis/update-trained-model-deployment.asciidoc:53
 
 [source, python]
 ----

diff --git a/docs/examples/77b90f6787195767b6da60d8532714b4.asciidoc b/docs/examples/77b90f6787195767b6da60d8532714b4.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:552
+// inference/put-inference.asciidoc:623
 
 [source, python]
 ----

diff --git a/docs/examples/7fef68840761c6982c14ad7af96caf37.asciidoc b/docs/examples/7fef68840761c6982c14ad7af96caf37.asciidoc
@@ -1,4 +1,4 @@
-// mapping/types/nested.asciidoc:22
+// mapping/types/nested.asciidoc:24
 
 [source, python]
 ----

diff --git a/docs/examples/8575c966b004fb124c7afd6bb5827b50.asciidoc b/docs/examples/8575c966b004fb124c7afd6bb5827b50.asciidoc
diff --git a/docs/examples/8619bd17bbfe33490b1f277007f654db.asciidoc b/docs/examples/8619bd17bbfe33490b1f277007f654db.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:353
+// inference/put-inference.asciidoc:424
 
 [source, python]
 ----

diff --git a/docs/examples/87733deeea4b441b595d19a0f97346f0.asciidoc b/docs/examples/87733deeea4b441b595d19a0f97346f0.asciidoc
@@ -1,4 +1,4 @@
-// health/health.asciidoc:471
+// health/health.asciidoc:474
 
 [source, python]
 ----

diff --git a/docs/examples/9a203aae3e1412d919546276fb52a5ca.asciidoc b/docs/examples/9a203aae3e1412d919546276fb52a5ca.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:335
+// inference/put-inference.asciidoc:406
 
 [source, python]
 ----

diff --git a/docs/examples/9d79645ab3a9da3f63c54a1516214a5a.asciidoc b/docs/examples/9d79645ab3a9da3f63c54a1516214a5a.asciidoc
@@ -1,4 +1,4 @@
-// health/health.asciidoc:463
+// health/health.asciidoc:466
 
 [source, python]
 ----

diff --git a/docs/examples/9f16fca9813304e398ee052aa857dbcd.asciidoc b/docs/examples/9f16fca9813304e398ee052aa857dbcd.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:513
+// inference/put-inference.asciidoc:584
 
 [source, python]
 ----

diff --git a/docs/examples/bcc75fc01b45e482638c65b8fbdf09fa.asciidoc b/docs/examples/bcc75fc01b45e482638c65b8fbdf09fa.asciidoc
diff --git a/docs/examples/cedb56a71cc743d80263ce352bb21720.asciidoc b/docs/examples/cedb56a71cc743d80263ce352bb21720.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:406
+// inference/put-inference.asciidoc:477
 
 [source, python]
 ----

diff --git a/docs/examples/d04f0c8c44e8b4fb55f2e7d9d05977e7.asciidoc b/docs/examples/d04f0c8c44e8b4fb55f2e7d9d05977e7.asciidoc
diff --git a/docs/examples/eee6110831c08b9c1b3f56b24656e95b.asciidoc b/docs/examples/eee6110831c08b9c1b3f56b24656e95b.asciidoc
@@ -1,4 +1,4 @@
-// inference/put-inference.asciidoc:445
+// inference/put-inference.asciidoc:516
 
 [source, python]
 ----

diff --git a/docs/examples/f57ce7de0946e9416ddb9150e95f4b74.asciidoc b/docs/examples/f57ce7de0946e9416ddb9150e95f4b74.asciidoc
@@ -0,0 +1,19 @@
+// inference/put-inference.asciidoc:641
+
+[source, python]
+----
+resp = client.inference.put_model(
+    task_type="completion",
+    inference_id="azure_openai_completion",
+    body={
+        "service": "azureopenai",
+        "service_settings": {
+            "api_key": "<api_key>",
+            "resource_name": "<resource_name>",
+            "deployment_id": "<deployment_id>",
+            "api_version": "2024-02-01",
+        },
+    },
+)
+print(resp)
+----
diff --git a/docs/guide/release-notes.asciidoc b/docs/guide/release-notes.asciidoc
@@ -1,6 +1,7 @@
 [[release-notes]]
 == Release notes
 
+* <<rn-8-13-2>>
 * <<rn-8-13-1>>
 * <<rn-8-13-0>>
 * <<rn-8-12-1>>
@@ -37,21 +38,28 @@
 * <<rn-8-1-0>>
 * <<rn-8-0-0>>
 
+[discrete]
+[[rn-8-13-2]]
+=== 8.13.2 (2024-05-24)
+
+- Added the `ml.update_trained_model_deployment` API
+- Marked Requests 2.32.2 as incompatible with the Elasticsearch client
+
 [discrete]
 [[rn-8-13-1]]
 === 8.13.1 (2024-05-03)
 
-- Added ``force_synthetic_source`` to the Get API
-- Added ``wait_for_completion`` to the Create trained model API
-- Added ``typed_keys`` to the Query API key information API
+- Added `force_synthetic_source` to the Get API
+- Added `wait_for_completion` to the Create trained model API
+- Added `typed_keys` to the Query API key information API
 
 [discrete]
 [[rn-8-13-0]]
 === 8.13.0 (2024-03-22)
 
 - Added native OpenTelemetry support
-- Added optional ``orjson`` (a fast, correct JSON library) serialization support
-- Added the `text_strcuture.test_grok_pattern` API
+- Added optional `orjson` (a fast, correct JSON library) serialization support
+- Added the `text_structure.test_grok_pattern` API
 - Added the `indices.resolve_cluster` API
 - Renamed the `model_id` parameter to `inference_id` in the `inference` APIs
 - Changed all `synonyms` APIs from **experimental** to **stable**.

diff --git a/elasticsearch/_async/client/ml.py b/elasticsearch/_async/client/ml.py
@@ -5043,6 +5043,62 @@ async def update_model_snapshot(
             path_parts=__path_parts,
         )
 
+    @_rewrite_parameters(
+        body_fields=("number_of_allocations",),
+    )
+    async def update_trained_model_deployment(
+        self,
+        *,
+        model_id: str,
+        error_trace: t.Optional[bool] = None,
+        filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
+        human: t.Optional[bool] = None,
+        number_of_allocations: t.Optional[int] = None,
+        pretty: t.Optional[bool] = None,
+        body: t.Optional[t.Dict[str, t.Any]] = None,
+    ) -> ObjectApiResponse[t.Any]:
+        """
+        Updates certain properties of trained model deployment.
+
+        `<https://www.elastic.co/guide/en/elasticsearch/reference/8.13/update-trained-model-deployment.html>`_
+
+        :param model_id: The unique identifier of the trained model. Currently, only
+            PyTorch models are supported.
+        :param number_of_allocations: The number of model allocations on each node where
+            the model is deployed. All allocations on a node share the same copy of the
+            model in memory but use a separate set of threads to evaluate the model.
+            Increasing this value generally increases the throughput. If this setting
+            is greater than the number of hardware threads it will automatically be changed
+            to a value less than the number of hardware threads.
+        """
+        if model_id in SKIP_IN_PATH:
+            raise ValueError("Empty value passed for parameter 'model_id'")
+        __path_parts: t.Dict[str, str] = {"model_id": _quote(model_id)}
+        __path = f'/_ml/trained_models/{__path_parts["model_id"]}/deployment/_update'
+        __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 not __body:
+            if number_of_allocations is not None:
+                __body["number_of_allocations"] = number_of_allocations
+        __headers = {"accept": "application/json", "content-type": "application/json"}
+        return await self.perform_request(  # type: ignore[return-value]
+            "POST",
+            __path,
+            params=__query,
+            headers=__headers,
+            body=__body,
+            endpoint_id="ml.update_trained_model_deployment",
+            path_parts=__path_parts,
+        )
+
     @_rewrite_parameters()
     async def upgrade_job_snapshot(
         self,