[[["์ดํดํ๊ธฐ ์ฌ์","easyToUnderstand","thumb-up"],["๋ฌธ์ ๊ฐ ํด๊ฒฐ๋จ","solvedMyProblem","thumb-up"],["๊ธฐํ","otherUp","thumb-up"]],[["์ดํดํ๊ธฐ ์ด๋ ค์","hardToUnderstand","thumb-down"],["์๋ชป๋ ์ ๋ณด ๋๋ ์ํ ์ฝ๋","incorrectInformationOrSampleCode","thumb-down"],["ํ์ํ ์ ๋ณด/์ํ์ด ์์","missingTheInformationSamplesINeed","thumb-down"],["๋ฒ์ญ ๋ฌธ์ ","translationIssue","thumb-down"],["๊ธฐํ","otherDown","thumb-down"]],["์ต์ข ์ ๋ฐ์ดํธ: 2024-12-21(UTC)"],[[["\u003cp\u003eVertex AI Search for media offers media recommendations and media search capabilities, enabling personalized content discovery and advanced search functionalities tailored for media content.\u003c/p\u003e\n"],["\u003cp\u003eMedia apps in Vertex AI Search require user event data to personalize recommendations and refine search result rankings, ensuring content relevance for the audience.\u003c/p\u003e\n"],["\u003cp\u003eMedia apps need structured media metadata that either follows a predefined schema with specific media fields or a custom schema with mapped required properties like \u003ccode\u003etitle\u003c/code\u003e, \u003ccode\u003ecategory\u003c/code\u003e, \u003ccode\u003euri\u003c/code\u003e, \u003ccode\u003emedia_available_time\u003c/code\u003e, and \u003ccode\u003emedia_duration\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eMedia recommendation apps allow you to customize the type of recommendation generated, such as suggesting similar content or the most popular content, and choose optimization objectives like increasing click-through or conversion rates.\u003c/p\u003e\n"],["\u003cp\u003eVertex AI Search provides step-by-step tutorials and checklists for media apps, guiding users through app creation and workflows specific to media search and recommendations, such as structured data and user events.\u003c/p\u003e\n"]]],[],null,["# Introduction to media search and recommendations\n\nThis page introduces and describes the capabilities of Vertex AI Search\nfor media. The page also provides links to more information,\ntutorials and checklists, to get you started with\nVertex AI Search for media.\n\nVertex AI Search includes two capabilities specific for the media\nindustry:\n\n- **Media recommendations.** Get recommendations for media content such as\n videos, news, and music. With media recommendations, audiences can discover\n more personalized content, like what to watch or read next, with\n Google-quality results customized using optimization objectives.\n\n- **Media search.** Get Google-quality search results with advanced query and\n document understanding designed for media content.\n\n| **Note:** Don't be misled by the product name. With Vertex AI Search, you can create recommendations apps as well as search apps.\n\nKey features of media apps\n--------------------------\n\nThere are many similarities between media apps and custom apps\nin Vertex AI Search. Here are some key features of media\napps:\n\n- **Media apps require user events.** You upload user events to personalize\n recommendations and rank search results for your audience.\n\n- **Media apps require media metadata to conform to a predefined schema or\n to use a custom schema that contains a minimum set of key properties.**\n\n - **Predefined schema.** This lets recommendations and search ranking\n use Google-defined, media-specific fields such as content ratings,\n aggregated ratings, persons, and production year to help generate results\n based on media engagement.\n\n - **Custom schema.** The custom schema gives you more\n flexibility than the predefined schema. However, your schema fields must\n map to the following *required* key properties: `title`, `category`, `uri`,\n `media_available_time`, and `media_duration`. The `category` property\n must be an array of strings, and the other four properties are strings.\n\n In addition to the required key properties, Google recommends that you\n map as many other schema fields as possible to the *suggested* key\n properties. The suggested key properties represent similar media metadata\n to that in the predefined schema---for example, content ratings, aggregated\n ratings, persons, and production year.\n- **Media recommendations apps offer you a choice of recommendation type.**\n Media recommendations apps let you choose what kind of recommendation to\n generate, such as recommending other content that users might like, similar\n items, or the most popular items.\n\n- **Media recommendations apps offer you a choice of optimization objectives.**\n For example, you can decide whether to optimize recommendations for\n click-through-rate to increase the number of interactions with content or\n for conversion rate to increase the consumption of content.\n\nThe following table outlines some functional differences between media and\ncustom data stores.\n\nFor more information, see [About media data stores and\ndocuments](/generative-ai-app-builder/docs/media-documents) and [About apps and data\nstores](/generative-ai-app-builder/docs/create-datastore-ingest).\n\nGetting started tutorials\n-------------------------\n\nIf you are new to Vertex AI Search, try out the getting\nstarted tutorials. These tutorials guide you step-by-step through the creation\nof an app. Data (documents and user events) are provided for the tutorials so\nall you need is a Google Cloud project and a billing account to create your\nfirst app:\n\n- [Get started with media recommendations](/generative-ai-app-builder/docs/try-media-recommendations)\n- [Get started with media search](/generative-ai-app-builder/docs/try-media-search)\n\nChecklists\n----------\n\nThere is a lot of commonality between working with media apps and working with\ncustom apps, but some features apply only to custom apps and\nother features only to media apps.\n\nUse the following checklists to guide you through typical workflows specific\nto media:\n\n- [Media search checklist](/generative-ai-app-builder/docs/media-search-checklist)\n\n- [Media recommendations checklist](/generative-ai-app-builder/docs/media-recommendations-checklist)"]]
