From 6bf09889c120f30f9242aa4af9a5e3f0b260053d Mon Sep 17 00:00:00 2001 From: Elastic Machine Date: Mon, 22 Dec 2025 06:03:32 +0000 Subject: [PATCH] Auto-generated API code --- docs/reference.asciidoc | 4 ++-- src/api/api/inference.ts | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/reference.asciidoc b/docs/reference.asciidoc index 0701e039d..d444e94e1 100644 --- a/docs/reference.asciidoc +++ b/docs/reference.asciidoc @@ -8146,12 +8146,12 @@ 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. {ref}/chat-completion-inference-api.html[Endpoint documentation] [source,ts] diff --git a/src/api/api/inference.ts b/src/api/api/inference.ts index c81794984..343061ce1 100644 --- a/src/api/api/inference.ts +++ b/src/api/api/inference.ts @@ -45,7 +45,7 @@ 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/guide/en/elasticsearch/reference/8.19/chat-completion-inference-api.html | Elasticsearch API documentation} */ async chatCompletionUnified (this: That, params: T.InferenceChatCompletionUnifiedRequest | TB.InferenceChatCompletionUnifiedRequest, options?: TransportRequestOptionsWithOutMeta): Promise