From 1180764daa8a14d109d105f12d39d440f68cb8c1 Mon Sep 17 00:00:00 2001 From: Elastic Machine Date: Mon, 22 Dec 2025 06:03:34 +0000 Subject: [PATCH] Auto-generated API code --- docs/reference/api-reference.md | 4 ++-- src/api/api/inference.ts | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/reference/api-reference.md b/docs/reference/api-reference.md index fe869f90b..13d5fd38f 100644 --- a/docs/reference/api-reference.md +++ b/docs/reference/api-reference.md @@ -7628,12 +7628,12 @@ Supports a list of values, such as `open,hidden`. Perform chat completion inference. The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation. -It only works with the `chat_completion` task type for `openai` and `elastic` inference services. +It only works with the `chat_completion` task type. NOTE: The `chat_completion` task type is only available within the _stream API and only supports streaming. The Chat completion inference API and the Stream inference API differ in their response structure and capabilities. The Chat completion inference API provides more comprehensive customization options through more fields and function calling support. -If you use the `openai`, `hugging_face` or the `elastic` service, use the Chat completion inference API. +To determine whether a given inference service supports this task type, please see the page for that service. [Endpoint documentation](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-unified-inference) diff --git a/src/api/api/inference.ts b/src/api/api/inference.ts index dafa1395d..8cf3c0878 100644 --- a/src/api/api/inference.ts +++ b/src/api/api/inference.ts @@ -486,7 +486,7 @@ export default class Inference { } /** - * Perform chat completion inference. The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation. It only works with the `chat_completion` task type for `openai` and `elastic` inference services. NOTE: The `chat_completion` task type is only available within the _stream API and only supports streaming. The Chat completion inference API and the Stream inference API differ in their response structure and capabilities. The Chat completion inference API provides more comprehensive customization options through more fields and function calling support. If you use the `openai`, `hugging_face` or the `elastic` service, use the Chat completion inference API. + * Perform chat completion inference. The chat completion inference API enables real-time responses for chat completion tasks by delivering answers incrementally, reducing response times during computation. It only works with the `chat_completion` task type. NOTE: The `chat_completion` task type is only available within the _stream API and only supports streaming. The Chat completion inference API and the Stream inference API differ in their response structure and capabilities. The Chat completion inference API provides more comprehensive customization options through more fields and function calling support. To determine whether a given inference service supports this task type, please see the page for that service. * @see {@link https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-unified-inference | Elasticsearch API documentation} */ async chatCompletionUnified (this: That, params: T.InferenceChatCompletionUnifiedRequest, options?: TransportRequestOptionsWithOutMeta): Promise