Introduction to Vertex AI Search

This page introduces the key search and recommendations features of Vertex AI Search.

Information retrieval using AI and LLMs

Vertex AI Search brings together the power of deep information retrieval, state-of-the-art natural language processing, and the latest in large language model (LLM) processing to understand user intent and return the most relevant results for the user.

With Vertex AI Search, you can build a Google-quality search app on your own data and embed a search bar in your web pages or app.

With Recommendations, you can build a recommendations app on your own data that will suggest content similar to the content that the user is currently viewing.

An easy experience to get started

Vertex AI Search makes it easy to get started with high-quality search or recommendations based on data that you provide. As part of the setup experience, you can:

  • Use your existing Google Account or sign up for one.
  • Use your existing Google Cloud project or create one.
  • Create an app and attach a data store to it. Provide data to search or recommend by entering the URLs for your website content, importing your data from BigQuery or Cloud Storage, or uploading through RESTful CRUD APIs. Syncing data from Jira, Salesforce, or Confluence is available in Preview with allowlist.
  • Embed JavaScript widgets and API samples to integrate search or recommendations into your website or applications.

Data stores and apps

With Vertex AI Search, you create a search or recommendations app and attach it to a data store. You import your data into a data store and index your data. Apps and data stores have a one-to-one relationship.

There are three kinds of data stores that you can create, based on the type of data you use. Each data store can contain one type of data:

  • Website data: You can provide domains such as yourexamplewebsite.com/faq and yourexamplewebsite.com/events and enable search or recommendations over the content at those domains.
  • Structured data: A data store with structured data enables semantic search or recommendations over structured data such as a BigQuery table or NDJSON files. For example, you can enable search or recommendations over a product catalog for your ecommerce experience, a movie catalog for movie search or recommendations, or a directory of doctors for provider search or recommendations.
  • Unstructured data: An unstructured data store enables semantic search or recommendations over data such as documents and images. For example, a financial institution can enable search or recommendations over their private corpus of financial research publications, or a biotech company can enable search or recommendations over their private repository of medical research.

For more information, see About apps and data stores.

Google Cloud console or the API?

You can implement Vertex AI Search in any of the following ways:

  • Use the Google Cloud console. Use the Search and Conversation page of the console for a quick-start experience using a web interface. From the console, you can create your search app, import your data, test the user experience, and view analytics.
  • Use the Vertex AI Search and Conversation API. Use the Vertex AI Search and Conversation API when you're ready to integrate search or recommendations into your website or applications.
  • Use both the Google Cloud console and the API. You can set up your app and import your data using the console, for example, and then use the API to test the user experience and integrate it into your website or application.

What's next