Set up a Google Cloud project, turn on Vertex AI Agent Builder, and set up access control for your project. You can use an existing Google Cloud project if you have one already.
Actions
- Review Before you begin and confirm that you have completed the steps.
Prepare to import your source FHIR R4 data from a Cloud Healthcare API data store to your Vertex AI Search data store.
Actions
Review the information about supported data and the relationship between healthcare search apps and data stores in About apps and data stores.
Prepare your source data according to the requirements in Prepare data for ingestion.
Create a data store and then import your data into it. You can perform a one-time batch import or set up a streaming import (Preview).
Actions
- To create a data store and import data into it and later connect it to a healthcare search app, follow the instructions in Create a healthcare search data store.
Create your healthcare search app and connect it to your new data store.
Actions
Vertex AI Search provides options to customize your search widget.
Actions
Depending on your use case and whether you plan to deploy the out-of-the-box search widget or integrate search API calls into your own code, Vertex AI Search provides several options for configuration.
Search widget results. Select the whether to perform a basic search or to search with an answer using LLMs. Applicable for a search widget. See Configure results for the search widget.
Autocomplete. Set up autocomplete suggestions to receive helpful query suggestions. See Configure autocomplete (Preview).
Preview your search results to check if your app configurations are working as expected. You can search using keywords and natural language queries. You can also choose to get a generative AI answer.
Actions
Review the subset of FHIR resources, resource references, and elements that Vertex AI Search supports. See Healthcare FHIR R4 data schema reference.
Preview your search results, using the console or the API.
Console. Use the Agent Builder console Preview page to preview how search widget configurations affect your results. See the Console instructions in Search healthcare data.
API. If you're integrating API calls into your application, make API calls to preview your search configurations. See the REST instructions in Search healthcare data.
If you plan to deploy your app by integrating search API calls into your own code, Vertex AI Search lets you customize the results.
Actions
Configure your search requests with the following options:
- Filter results. See Filter healthcare search.
When you are happy with the preview version of your search app, share it with your users by deploying it to your website.
Actions
You can deploy your search app in either of the following ways:
Embed the search widget into your website. Vertex AI Search provides code that you can copy into your website or web application. This deploys the search widget. You can preview search results in the console. See Add the search widget to a webpage.
Integrate search API calls into your server or application. For full control over how your search results are displayed, you can integrate API calls into your server or applications. For more information about making API calls, see Search healthcare data. For client library resources, see Vertex AI Agent Builder client libraries.
You can maintain your app to ensure that latest and necessary data is available in your data store.
Actions
- To refresh your data, see Refresh healthcare data. Refresh your data only if you perform batch imports. You can skip this step if you have set up a streaming import.