[Backport 8.19] Add timeout params for PUT inference and POST inference/_stream

specification/inference/put/PutRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import { InferenceEndpoint } from '@inference/_types/Services'
 import { TaskType } from '@inference/_types/TaskType'
 
@@ -74,6 +75,13 @@ export interface Request extends RequestBase {
      */
     inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   /** @codegen_name inference_config */
   body: InferenceEndpoint
 }

specification/inference/put_alibabacloud/PutAlibabaCloudRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   AlibabaCloudServiceSettings,
   AlibabaCloudServiceType,
@@ -54,6 +55,13 @@ export interface Request extends RequestBase {
      */
     alibabacloud_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_amazonbedrock/PutAmazonBedrockRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   AmazonBedrockServiceSettings,
   AmazonBedrockServiceType,
@@ -57,6 +58,13 @@ export interface Request extends RequestBase {
      */
     amazonbedrock_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_anthropic/PutAnthropicRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   AnthropicServiceSettings,
   AnthropicServiceType,
@@ -55,6 +56,13 @@ export interface Request extends RequestBase {
      */
     anthropic_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_azureaistudio/PutAzureAiStudioRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   AzureAiStudioServiceSettings,
   AzureAiStudioServiceType,
@@ -54,6 +55,13 @@ export interface Request extends RequestBase {
      */
     azureaistudio_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_azureopenai/PutAzureOpenAiRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   AzureOpenAIServiceSettings,
   AzureOpenAIServiceType,
@@ -62,6 +63,13 @@ export interface Request extends RequestBase {
      */
     azureopenai_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_cohere/PutCohereRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   CohereServiceSettings,
   CohereServiceType,
@@ -54,6 +55,13 @@ export interface Request extends RequestBase {
      */
     cohere_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_deepseek/PutDeepSeekRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   DeepSeekServiceSettings,
   DeepSeekServiceType
@@ -53,6 +54,13 @@ export interface Request extends RequestBase {
      */
     deepseek_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_elasticsearch/PutElasticsearchRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   ElasticsearchServiceSettings,
   ElasticsearchServiceType,
@@ -68,6 +69,13 @@ export interface Request extends RequestBase {
      */
     elasticsearch_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_elser/PutElserRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   ElserServiceSettings,
   ElserServiceType,
@@ -68,6 +69,13 @@ export interface Request extends RequestBase {
      */
     elser_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_googleaistudio/PutGoogleAiStudioRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   GoogleAiServiceType,
   GoogleAiStudioServiceSettings,
@@ -53,6 +54,13 @@ export interface Request extends RequestBase {
      */
     googleaistudio_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_googlevertexai/PutGoogleVertexAiRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   GoogleVertexAIServiceSettings,
   GoogleVertexAIServiceType,
@@ -54,6 +55,13 @@ export interface Request extends RequestBase {
      */
     googlevertexai_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_hugging_face/PutHuggingFaceRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   HuggingFaceServiceSettings,
   HuggingFaceServiceType,
@@ -90,6 +91,13 @@ export interface Request extends RequestBase {
      */
     huggingface_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_jinaai/PutJinaAiRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   JinaAIServiceSettings,
   JinaAIServiceType,
@@ -57,6 +58,13 @@ export interface Request extends RequestBase {
      */
     jinaai_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_mistral/PutMistralRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   MistralServiceSettings,
   MistralServiceType,
@@ -53,6 +54,13 @@ export interface Request extends RequestBase {
      */
     mistral_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_openai/PutOpenAiRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   OpenAIServiceSettings,
   OpenAIServiceType,
@@ -55,6 +56,13 @@ export interface Request extends RequestBase {
      */
     openai_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.

specification/inference/put_voyageai/PutVoyageAIRequest.ts

@@ -19,6 +19,7 @@
 
 import { RequestBase } from '@_types/Base'
 import { Id } from '@_types/common'
+import { Duration } from '@_types/Time'
 import {
   VoyageAIServiceSettings,
   VoyageAIServiceType,
@@ -56,6 +57,13 @@ export interface Request extends RequestBase {
      */
     voyageai_inference_id: Id
   }
+  query_parameters: {
+    /**
+     * Specifies the amount of time to wait for the inference endpoint to be created.
+     * @server_default 30s
+     */
+    timeout?: Duration
+  }
   body: {
     /**
      * The chunking configuration object.