|
| 1 | +/* |
| 2 | + * Licensed to Elasticsearch B.V. under one or more contributor |
| 3 | + * license agreements. See the NOTICE file distributed with |
| 4 | + * this work for additional information regarding copyright |
| 5 | + * ownership. Elasticsearch B.V. licenses this file to you under |
| 6 | + * the Apache License, Version 2.0 (the "License"); you may |
| 7 | + * not use this file except in compliance with the License. |
| 8 | + * You may obtain a copy of the License at |
| 9 | + * |
| 10 | + * http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | + * |
| 12 | + * Unless required by applicable law or agreed to in writing, |
| 13 | + * software distributed under the License is distributed on an |
| 14 | + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 15 | + * KIND, either express or implied. See the License for the |
| 16 | + * specific language governing permissions and limitations |
| 17 | + * under the License. |
| 18 | + */ |
| 19 | + |
| 20 | +import { RequestBase } from '@_types/Base' |
| 21 | +import { Id } from '@_types/common' |
| 22 | +import { integer } from '@_types/Numeric' |
| 23 | + |
| 24 | +/** |
| 25 | + * Create a Watsonx inference endpoint. |
| 26 | + * |
| 27 | + * Creates an inference endpoint to perform an inference task with the `watsonxai` service. |
| 28 | + * The only valid task type for the model to perform is `text_embedding`. |
| 29 | + * You need an IBM Cloud Databases for Elasticsearch deployment to use the `watsonxai` inference service. |
| 30 | + * You can provision one through the IBM catalog, the Cloud Databases CLI plug-in, the Cloud Databases API, or Terraform. |
| 31 | + * |
| 32 | + * When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. |
| 33 | + * After creating the endpoint, wait for the model deployment to complete before using it. |
| 34 | + * To verify the deployment status, use the get trained model statistics API. |
| 35 | + * Look for `"state": "fully_allocated"` in the response and ensure that the `"allocation_count"` matches the `"target_allocation_count"`. |
| 36 | + * Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources. |
| 37 | + * @rest_spec_name inference.put_watsonx |
| 38 | + * @availability stack since=8.11.0 stability=stable visibility=public |
| 39 | + * @availability serverless stability=stable visibility=public |
| 40 | + * @cluster_privileges manage_inference |
| 41 | + * @doc_id inference-api-put-watsonx |
| 42 | + */ |
| 43 | +export interface Request extends RequestBase { |
| 44 | + urls: [ |
| 45 | + { |
| 46 | + path: '/_inference/text_embedding/{watsonx_inference_id}' |
| 47 | + methods: ['PUT'] |
| 48 | + } |
| 49 | + ] |
| 50 | + path_parts: { |
| 51 | + /** |
| 52 | + * The unique identifier of the inference endpoint. |
| 53 | + */ |
| 54 | + watsonx_inference_id: Id |
| 55 | + } |
| 56 | + body: { |
| 57 | + /** |
| 58 | + * The type of service supported for the specified task type. In this case, `watsonxai`. |
| 59 | + */ |
| 60 | + service: ServiceType |
| 61 | + /** |
| 62 | + * Settings used to install the inference model. These settings are specific to the `watsonxai` service. |
| 63 | + */ |
| 64 | + service_settings: WatsonxServiceSettings |
| 65 | + } |
| 66 | +} |
| 67 | + |
| 68 | +export enum ServiceType { |
| 69 | + watsonxai |
| 70 | +} |
| 71 | + |
| 72 | +export class RateLimitSetting { |
| 73 | + /** |
| 74 | + * By default, the `watsonxai` service sets the number of requests allowed per minute to 120. |
| 75 | + * @server_default 120 |
| 76 | + */ |
| 77 | + requests_per_minute?: integer |
| 78 | +} |
| 79 | + |
| 80 | +export class WatsonxServiceSettings { |
| 81 | + /** |
| 82 | + * A valid API key of your Watsonx account. |
| 83 | + * You can find your Watsonx API keys or you can create a new one on the API keys page. |
| 84 | + * |
| 85 | + * IMPORTANT: You need to provide the API key only once, during the inference model creation. |
| 86 | + * The get inference endpoint API does not retrieve your API key. |
| 87 | + * After creating the inference model, you cannot change the associated API key. |
| 88 | + * If you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key. |
| 89 | + * @ext_doc_id watsonx-api-keys |
| 90 | + */ |
| 91 | + api_key: string |
| 92 | + /** |
| 93 | + * A version parameter that takes a version date in the format of `YYYY-MM-DD`. |
| 94 | + * For the active version data parameters, refer to the Wastonx documentation. |
| 95 | + * @ext_doc_id watsonx-api-version |
| 96 | + */ |
| 97 | + api_version: string |
| 98 | + /** |
| 99 | + * The name of the model to use for the inference task. |
| 100 | + * Refer to the IBM Embedding Models section in the Watsonx documentation for the list of available text embedding models. |
| 101 | + * @ext_doc_id watsonx-api-models |
| 102 | + */ |
| 103 | + model_id: string |
| 104 | + /** |
| 105 | + * The identifier of the IBM Cloud project to use for the inference task. |
| 106 | + */ |
| 107 | + project_id: string |
| 108 | + /** |
| 109 | + * This setting helps to minimize the number of rate limit errors returned from Watsonx. |
| 110 | + */ |
| 111 | + rate_limit?: RateLimitSetting |
| 112 | + /** |
| 113 | + * The URL of the inference endpoint that you created on Watsonx. |
| 114 | + */ |
| 115 | + url: string |
| 116 | +} |
0 commit comments