elastic · JoshMock · Apr 7, 2025 · Apr 7, 2025
diff --git a/docs/doc_examples/120fcf9f55128d6a81d5e87a9c235bbd.asciidoc b/docs/doc_examples/120fcf9f55128d6a81d5e87a9c235bbd.asciidoc
@@ -3,16 +3,17 @@
 
 [source, js]
 ----
-const response = await client.inference.streamInference({
-  task_type: "chat_completion",
+const response = await client.inference.chatCompletionUnified({
   inference_id: "openai-completion",
-  model: "gpt-4o",
-  messages: [
-    {
-      role: "user",
-      content: "What is Elastic?",
-    },
-  ],
+  chat_completion_request: {
+    model: "gpt-4o",
+    messages: [
+      {
+        role: "user",
+        content: "What is Elastic?",
+      },
+    ],
+  },
 });
 console.log(response);
 ----
diff --git a/docs/doc_examples/13ecdf99114098c76b050397d9c3d4e6.asciidoc b/docs/doc_examples/13ecdf99114098c76b050397d9c3d4e6.asciidoc
@@ -3,8 +3,7 @@
 
 [source, js]
 ----
-const response = await client.inference.inference({
-  task_type: "sparse_embedding",
+const response = await client.inference.sparseEmbedding({
   inference_id: "my-elser-model",
   input:
     "The sky above the port was the color of television tuned to a dead channel.",

diff --git a/docs/doc_examples/141ef0ebaa3b0772892b79b9bb85efb0.asciidoc b/docs/doc_examples/141ef0ebaa3b0772892b79b9bb85efb0.asciidoc
@@ -3,9 +3,8 @@
 
 [source, js]
 ----
-const response = await client.inference.put({
-  task_type: "my-inference-endpoint",
-  inference_id: "_update",
+const response = await client.inference.update({
+  inference_id: "my-inference-endpoint",
   inference_config: {
     service_settings: {
       api_key: "<API_KEY>",

diff --git a/docs/doc_examples/45954b8aaedfed57012be8b6538b0a24.asciidoc b/docs/doc_examples/45954b8aaedfed57012be8b6538b0a24.asciidoc
@@ -3,42 +3,43 @@
 
 [source, js]
 ----
-const response = await client.inference.streamInference({
-  task_type: "chat_completion",
+const response = await client.inference.chatCompletionUnified({
   inference_id: "openai-completion",
-  messages: [
-    {
-      role: "user",
-      content: [
-        {
-          type: "text",
-          text: "What's the price of a scarf?",
+  chat_completion_request: {
+    messages: [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "What's the price of a scarf?",
+          },
+        ],
+      },
+    ],
+    tools: [
+      {
+        type: "function",
+        function: {
+          name: "get_current_price",
+          description: "Get the current price of a item",
+          parameters: {
+            type: "object",
+            properties: {
+              item: {
+                id: "123",
+              },
+            },
+          },
         },
-      ],
-    },
-  ],
-  tools: [
-    {
+      },
+    ],
+    tool_choice: {
       type: "function",
       function: {
         name: "get_current_price",
-        description: "Get the current price of a item",
-        parameters: {
-          type: "object",
-          properties: {
-            item: {
-              id: "123",
-            },
-          },
-        },
       },
     },
-  ],
-  tool_choice: {
-    type: "function",
-    function: {
-      name: "get_current_price",
-    },
   },
 });
 console.log(response);

diff --git a/docs/doc_examples/4b91ad7c9b44e07db4a4e81390f19ad3.asciidoc b/docs/doc_examples/4b91ad7c9b44e07db4a4e81390f19ad3.asciidoc
@@ -3,8 +3,7 @@
 
 [source, js]
 ----
-const response = await client.inference.streamInference({
-  task_type: "completion",
+const response = await client.inference.streamCompletion({
   inference_id: "openai-completion",
   input: "What is Elastic?",
 });

diff --git a/docs/doc_examples/7429b16221fe741fd31b0584786dd0b0.asciidoc b/docs/doc_examples/7429b16221fe741fd31b0584786dd0b0.asciidoc
@@ -3,8 +3,7 @@
 
 [source, js]
 ----
-const response = await client.inference.inference({
-  task_type: "text_embedding",
+const response = await client.inference.textEmbedding({
   inference_id: "my-cohere-endpoint",
   input:
     "The sky above the port was the color of television tuned to a dead channel.",

diff --git a/docs/doc_examples/82bb6c61dab959f4446dc5ecab7ecbdf.asciidoc b/docs/doc_examples/82bb6c61dab959f4446dc5ecab7ecbdf.asciidoc
@@ -3,30 +3,31 @@
 
 [source, js]
 ----
-const response = await client.inference.streamInference({
-  task_type: "chat_completion",
+const response = await client.inference.chatCompletionUnified({
   inference_id: "openai-completion",
-  messages: [
-    {
-      role: "assistant",
-      content: "Let's find out what the weather is",
-      tool_calls: [
-        {
-          id: "call_KcAjWtAww20AihPHphUh46Gd",
-          type: "function",
-          function: {
-            name: "get_current_weather",
-            arguments: '{"location":"Boston, MA"}',
+  chat_completion_request: {
+    messages: [
+      {
+        role: "assistant",
+        content: "Let's find out what the weather is",
+        tool_calls: [
+          {
+            id: "call_KcAjWtAww20AihPHphUh46Gd",
+            type: "function",
+            function: {
+              name: "get_current_weather",
+              arguments: '{"location":"Boston, MA"}',
+            },
           },
-        },
-      ],
-    },
-    {
-      role: "tool",
-      content: "The weather is cold",
-      tool_call_id: "call_KcAjWtAww20AihPHphUh46Gd",
-    },
-  ],
+        ],
+      },
+      {
+        role: "tool",
+        content: "The weather is cold",
+        tool_call_id: "call_KcAjWtAww20AihPHphUh46Gd",
+      },
+    ],
+  },
 });
 console.log(response);
 ----
diff --git a/docs/doc_examples/b45a8c6fc746e9c90fd181e69a605fad.asciidoc b/docs/doc_examples/b45a8c6fc746e9c90fd181e69a605fad.asciidoc
@@ -3,8 +3,7 @@
 
 [source, js]
 ----
-const response = await client.inference.inference({
-  task_type: "completion",
+const response = await client.inference.completion({
   inference_id: "openai_chat_completions",
   input: "What is Elastic?",
 });

diff --git a/docs/doc_examples/f1b24217b1d9ba6ea5e4fa6e6f412022.asciidoc b/docs/doc_examples/f1b24217b1d9ba6ea5e4fa6e6f412022.asciidoc
@@ -3,8 +3,7 @@
 
 [source, js]
 ----
-const response = await client.inference.inference({
-  task_type: "rerank",
+const response = await client.inference.rerank({
   inference_id: "cohere_rerank",
   input: ["luke", "like", "leia", "chewy", "r2d2", "star", "wars"],
   query: "star wars main character",

diff --git a/docs/reference/api-reference.md b/docs/reference/api-reference.md
@@ -7553,23 +7553,6 @@ client.inference.get({ ... })
 - **`task_type` (Optional, Enum("sparse_embedding" | "text_embedding" | "rerank" | "completion" | "chat_completion"))**: The task type
 - **`inference_id` (Optional, string)**: The inference Id
 
-## client.inference.postEisChatCompletion [_inference.post_eis_chat_completion]
-Perform a chat completion task through the Elastic Inference Service (EIS).
-
-Perform a chat completion inference task with the `elastic` service.
-
-[Endpoint documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-post-eis-chat-completion)
-
-```ts
-client.inference.postEisChatCompletion({ eis_inference_id })
-```
-
-### Arguments [_arguments_inference.post_eis_chat_completion]
-
-#### Request (object) [_request_inference.post_eis_chat_completion]
-- **`eis_inference_id` (string)**: The unique identifier of the inference endpoint.
-- **`chat_completion_request` (Optional, { messages, model, max_completion_tokens, stop, temperature, tool_choice, tools, top_p })**
-
 ## client.inference.put [_inference.put]
 Create an inference endpoint.
 When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
@@ -7776,26 +7759,6 @@ These settings are specific to the `cohere` service.
 - **`task_settings` (Optional, { input_type, return_documents, top_n, truncate })**: Settings to configure the inference task.
 These settings are specific to the task type you specified.
 
-## client.inference.putEis [_inference.put_eis]
-Create an Elastic Inference Service (EIS) inference endpoint.
-
-Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).
-
-[Endpoint documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put-eis)
-
-```ts
-client.inference.putEis({ task_type, eis_inference_id, service, service_settings })
-```
-
-### Arguments [_arguments_inference.put_eis]
-
-#### Request (object) [_request_inference.put_eis]
-- **`task_type` (Enum("chat_completion"))**: The type of the inference task that the model will perform.
-NOTE: The `chat_completion` task type only supports streaming and only through the _stream API.
-- **`eis_inference_id` (string)**: The unique identifier of the inference endpoint.
-- **`service` (Enum("elastic"))**: The type of service supported for the specified task type. In this case, `elastic`.
-- **`service_settings` ({ model_id, rate_limit })**: Settings used to install the inference model. These settings are specific to the `elastic` service.
-
 ## client.inference.putElasticsearch [_inference.put_elasticsearch]
 Create an Elasticsearch inference endpoint.