Deploys a model. If a model is already deployed, deploying it has no effect. A model can only serve prediction requests after it gets deployed. For article suggestion, custom model will not be used unless it is deployed.
This method is a long-running operation. The returned Operation type has the following method-specific fields:
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-27 UTC."],[[["This document outlines the process for deploying a conversation model, which is necessary for the model to serve prediction requests, and has no effect if already deployed."],["Deploying a model involves a long-running operation that returns an `Operation` type with specific metadata and an empty response."],["The HTTP request for deployment is a POST request to a specific endpoint, using the gRPC Transcoding syntax."],["The `name` parameter in the request is mandatory, specifying the conversation model to deploy in the format of `projects/\u003cProject ID\u003e/conversationModels/\u003cConversation Model ID\u003e`, and requires specific IAM permission."],["The request body for deploying a model must be empty, while a successful deployment returns an instance of the `Operation`."]]],[]]
