You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/Elastic.Clients.Elasticsearch/_Generated/Api/Inference/ChatCompletionUnifiedRequest.g.cs
+28
Original file line number
Diff line number
Diff line change
@@ -50,6 +50,20 @@ public override void Write(System.Text.Json.Utf8JsonWriter writer, Elastic.Clien
50
50
/// <para>
51
51
/// Perform chat completion inference
52
52
/// </para>
53
+
/// <para>
54
+
/// The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation.
55
+
/// It only works with the <c>chat_completion</c> task type for <c>openai</c> and <c>elastic</c> inference services.
56
+
/// </para>
57
+
/// <para>
58
+
/// 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, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.
59
+
/// 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.
60
+
/// </para>
61
+
/// <para>
62
+
/// NOTE: The <c>chat_completion</c> task type is only available within the _stream API and only supports streaming.
63
+
/// The Chat completion inference API and the Stream inference API differ in their response structure and capabilities.
64
+
/// The Chat completion inference API provides more comprehensive customization options through more fields and function calling support.
65
+
/// If you use the <c>openai</c> service or the <c>elastic</c> service, use the Chat completion inference API.
/// The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation.
131
+
/// It only works with the <c>chat_completion</c> task type for <c>openai</c> and <c>elastic</c> inference services.
132
+
/// </para>
133
+
/// <para>
134
+
/// 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, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.
135
+
/// 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.
136
+
/// </para>
137
+
/// <para>
138
+
/// NOTE: The <c>chat_completion</c> task type is only available within the _stream API and only supports streaming.
139
+
/// The Chat completion inference API and the Stream inference API differ in their response structure and capabilities.
140
+
/// The Chat completion inference API provides more comprehensive customization options through more fields and function calling support.
141
+
/// If you use the <c>openai</c> service or the <c>elastic</c> service, use the Chat completion inference API.
Copy file name to clipboardExpand all lines: src/Elastic.Clients.Elasticsearch/_Generated/Api/Inference/PutAlibabacloudRequest.g.cs
-14
Original file line number
Diff line number
Diff line change
@@ -99,13 +99,6 @@ public override void Write(System.Text.Json.Utf8JsonWriter writer, Elastic.Clien
99
99
/// <para>
100
100
/// Create an inference endpoint to perform an inference task with the <c>alibabacloud-ai-search</c> service.
101
101
/// </para>
102
-
/// <para>
103
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
104
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
105
-
/// To verify the deployment status, use the get trained model statistics API.
106
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
107
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
/// Create an inference endpoint to perform an inference task with the <c>alibabacloud-ai-search</c> service.
205
198
/// </para>
206
-
/// <para>
207
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
208
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
209
-
/// To verify the deployment status, use the get trained model statistics API.
210
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
211
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
Copy file name to clipboardExpand all lines: src/Elastic.Clients.Elasticsearch/_Generated/Api/Inference/PutAmazonbedrockRequest.g.cs
-14
Original file line number
Diff line number
Diff line change
@@ -103,13 +103,6 @@ public override void Write(System.Text.Json.Utf8JsonWriter writer, Elastic.Clien
103
103
/// info
104
104
/// 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.
105
105
/// </para>
106
-
/// <para>
107
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
108
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
109
-
/// To verify the deployment status, use the get trained model statistics API.
110
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
111
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
/// 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.
213
206
/// </para>
214
-
/// <para>
215
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
216
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
217
-
/// To verify the deployment status, use the get trained model statistics API.
218
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
219
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
Copy file name to clipboardExpand all lines: src/Elastic.Clients.Elasticsearch/_Generated/Api/Inference/PutAnthropicRequest.g.cs
-14
Original file line number
Diff line number
Diff line change
@@ -99,13 +99,6 @@ public override void Write(System.Text.Json.Utf8JsonWriter writer, Elastic.Clien
99
99
/// <para>
100
100
/// Create an inference endpoint to perform an inference task with the <c>anthropic</c> service.
101
101
/// </para>
102
-
/// <para>
103
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
104
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
105
-
/// To verify the deployment status, use the get trained model statistics API.
106
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
107
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
/// Create an inference endpoint to perform an inference task with the <c>anthropic</c> service.
206
199
/// </para>
207
-
/// <para>
208
-
/// When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.
209
-
/// After creating the endpoint, wait for the model deployment to complete before using it.
210
-
/// To verify the deployment status, use the get trained model statistics API.
211
-
/// Look for <c>"state": "fully_allocated"</c> in the response and ensure that the <c>"allocation_count"</c> matches the <c>"target_allocation_count"</c>.
212
-
/// Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.
0 commit comments