Console

1. In the Google Cloud console, go to theAI Applications page.

   AI Applications

2. In the navigation menu, clickData Stores.

3. Clickadd_boxCreate data store.

4. In theSelect a data source pane, selectHealthcare API (FHIR) as your data source.
5. To import data from your FHIR store, do one of the following:
   • Select the FHIR store from the list of available FHIR stores:
     1. Expand theFHIR store field.
     2. In this list, select a dataset that resides in apermitted location and then select a FHIR store that uses FHIR version R4.
   • Enter the FHIR store manually:
     1. Expand theFHIR store field.
     2. ClickEnter FHIR store manually.
     3. In theFHIR store name dialog, enter the full name of the FHIR store in the following format:

        project/PROJECT_ID/locations/LOCATION/datasets/DATASET_ID/fhirStores/FHIR_STORE_ID

     4. ClickSave.
6. In theSynchronization section, select one of the following options.This selection cannot be changed after the data store is created.
   • One time: to perform a one-time batch data import. For further incremental imports, seeRefresh healthcare data.
   • Streaming: to perform a near real-time streaming data import. To stream data, you must create a data connector, which is a type of a data store. To set up a streaming data store using the REST API, contact your customer engineer.
7. In theWhat is the schema for this data? section, select one ofthese options:
   • Google predefined schema: to retain the Google-defined schema configurations, such as indexability, searchability, and retrievability, for the supported FHIR resources and elements. After you select this option, you cannot update the schema after you create the data store. If you want to be able to change the schema after the data store creation, select theCustom schema option.
     1. ClickContinue.
     2. In theYour data store name field, enter a name for your data store.
     3. ClickCreate.

     The data store you created is listed on theData Stores page.

   • Custom schema: to define your own schema configurations, such as indexability, searchability, and retrievability, for the supported FHIR resources and elements. To set up a configurable schema, contact your customer engineer.
     1. ClickContinue.
     2. Review the schema, expand each field, and edit the field settings.
     3. ClickAdd new fields to add new fields on the supported FHIR resources. You cannot remove the fields provided in the Google-defined schema.
     4. ClickContinue.
     5. In theYour data connector name field, enter a name for your data connector.
     6. ClickCreate.

     The data connector you created is listed on theData Stores page. The source FHIR store is added as an entity within the data connector.

8. ClickContinue.

REST

1. Create a data store.

   curl -X POST\ -H "Authorization: Bearer $(gcloud auth print-access-token)" \ -H "Content-Type: application/json"\ -H "X-Goog-User-Project:PROJECT_ID" \"https://us-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/us/collections/default_collection/dataStores?dataStoreId=DATA_STORE_ID" \ -d '{    "displayName": "DATA_STORE_DISPLAY_NAME",    "industryVertical": "HEALTHCARE_FHIR",    "solutionTypes": ["SOLUTION_TYPE_SEARCH"],    "searchTier": "STANDARD",    "searchAddOns": ["LLM"],    "healthcareFhirConfig":      {        "enableConfigurableSchema":CONFIGURABLE_SCHEMA_TRUE|FALSE      }}'

   Replace the following:

   • PROJECT_ID: the ID of your Google Cloud project.
   • DATA_STORE_ID: the ID of the Vertex AI Search data store that you want to create. This ID can contain only lowercaseletters, digits, underscores, and hyphens.
   • DATA_STORE_DISPLAY_NAME: the display name of the Vertex AISearch data store that you want to create.
   • CONFIGURABLE_SCHEMA_TRUE|FALSE: a boolean when set totrue lets you configure the data store schema using theschema.update method.

   Response

   You should receive a JSON response similar to the following. If the valuefor thedone key istrue, it indicates that theoperation to create the data store was completed. Otherwise, the data storecreation operation was unsuccessful.

   {  "name": "OPERATION_ID",  "done": true}

2. If the source FHIR store and the target Vertex AI Search data storeare in the same Google Cloud project, call the following method to perform aone-time batch import. If they're not in the same project, go to the nextstep.

   curl -X POST \-H "Authorization: Bearer $(gcloud auth print-access-token)" \-H "Content-Type: application/json; charset=utf-8" \-H "X-Goog-User-Project:PROJECT_ID" \"https://us-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/us/dataStores/DATA_STORE_ID/branches/0/documents:import" \-d '{   "reconciliation_mode": "FULL",   "fhir_store_source": {"fhir_store": "projects/PROJECT_ID/locations/CLOUD_HEALTHCARE_DATASET_LOCATION/datasets/CLOUD_HEALTHCARE_DATASET_ID/fhirStores/FHIR_STORE_ID"}}'

   Replace the following:

   • PROJECT_ID: the ID of your Google Cloud project.
   • DATA_STORE_ID: the ID of the Vertex AI Search data store.
   • CLOUD_HEALTHCARE_DATASET_ID: the ID of the Cloud Healthcare API dataset that contains the source FHIR store.
   • CLOUD_HEALTHCARE_DATASET_LOCATION: the location of the Cloud Healthcare API dataset that contains the source FHIR store.
   • FHIR_STORE_ID: the ID of the Cloud Healthcare API FHIR R4 store.

   Response

   You should receive a JSON response similar to the following. The responsecontains an identifier for a long-running operation. Long-running operationsare returned when method calls might take a substantial amount of time tocomplete. Note the value ofIMPORT_OPERATION_ID. You need thisvalue toverify the status of the importorcancel an ongoing batch import.

     {    "name": "projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/operations/IMPORT_OPERATION_ID",    "metadata": {      "@type": "type.googleapis.com/google.cloud.discoveryengine.v1.ImportDocumentsMetadata"    }  }

3. If the source FHIR store and the target Vertex AI Search data storeare in different Google Cloud projects, call the following method to performa one-time batch import. If they're in the same project, go back to theprevious step.

   curl -X POST \-H "Authorization: Bearer $(gcloud auth print-access-token)" \-H "Content-Type: application/json; charset=utf-8" \-H "X-Goog-User-Project:PROJECT_ID" \"https://us-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/us/dataStores/DATA_STORE_ID/branches/0/documents:import" \-d '{   "reconciliation_mode": "FULL",   "fhir_store_source": {"fhir_store": "projects/SOURCE_PROJECT_ID/locations/CLOUD_HEALTHCARE_DATASET_LOCATION/datasets/CLOUD_HEALTHCARE_DATASET_ID/fhirStores/FHIR_STORE_ID"}}'

   Replace the following:

   • PROJECT_ID: the ID of the Google Cloud project that contains the Vertex AI Search data store.
   • DATA_STORE_ID: the ID of the Vertex AI Search data store.
   • SOURCE_PROJECT_ID: the ID of the Google Cloud project that contains the Cloud Healthcare API dataset and FHIR store.
   • CLOUD_HEALTHCARE_DATASET_ID: the ID of the Cloud Healthcare API dataset that contains the source FHIR store.
   • CLOUD_HEALTHCARE_DATASET_LOCATION: the location of the Cloud Healthcare API dataset that contains the source FHIR store.
   • FHIR_STORE_ID: the ID of the Cloud Healthcare API FHIR R4 store.

   Response

   You should receive a JSON response similar to the following. The responsecontains an identifier for a long-running operation. Long-runningoperations are returned when method calls might take a substantial amountof time to complete. Note the value ofIMPORT_OPERATION_ID. You needthis value toverify the status of the import.

   {  "name": "projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/operations/IMPORT_OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.discoveryengine.v1.ImportDocumentsMetadata"  }}

Python

For more information, see theVertex AI SearchPython API reference documentation.

To authenticate to Vertex AI Search, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

Create a data store

fromgoogle.api_core.client_optionsimportClientOptionsfromgoogle.cloudimportdiscoveryengine# TODO(developer): Uncomment these variables before running the sample.# project_id = "YOUR_PROJECT_ID"# location = "YOUR_LOCATION" # Values: "global"# data_store_id = "YOUR_DATA_STORE_ID"defcreate_data_store_sample(project_id:str,location:str,data_store_id:str,)->str:#  For more information, refer to:# https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_storeclient_options=(ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")iflocation!="global"elseNone)# Create a clientclient=discoveryengine.DataStoreServiceClient(client_options=client_options)# The full resource name of the collection# e.g. projects/{project}/locations/{location}/collections/default_collectionparent=client.collection_path(project=project_id,location=location,collection="default_collection",)data_store=discoveryengine.DataStore(display_name="My Data Store",# Options: GENERIC, MEDIA, HEALTHCARE_FHIRindustry_vertical=discoveryengine.IndustryVertical.GENERIC,# Options: SOLUTION_TYPE_RECOMMENDATION, SOLUTION_TYPE_SEARCH, SOLUTION_TYPE_CHAT, SOLUTION_TYPE_GENERATIVE_CHATsolution_types=[discoveryengine.SolutionType.SOLUTION_TYPE_SEARCH],# TODO(developer): Update content_config based on data store type.# Options: NO_CONTENT, CONTENT_REQUIRED, PUBLIC_WEBSITEcontent_config=discoveryengine.DataStore.ContentConfig.CONTENT_REQUIRED,)request=discoveryengine.CreateDataStoreRequest(parent=parent,data_store_id=data_store_id,data_store=data_store,# Optional: For Advanced Site Search Only# create_advanced_site_search=True,)# Make the requestoperation=client.create_data_store(request=request)print(f"Waiting for operation to complete:{operation.operation.name}")response=operation.result()# After the operation is complete,# get information from operation metadatametadata=discoveryengine.CreateDataStoreMetadata(operation.metadata)# Handle the responseprint(response)print(metadata)returnoperation.operation.name

Import documents

fromgoogle.api_core.client_optionsimportClientOptionsfromgoogle.cloudimportdiscoveryengine# TODO(developer): Uncomment these variables before running the sample.# project_id = "YOUR_PROJECT_ID"# location = "YOUR_LOCATION" # Values: "us"# data_store_id = "YOUR_DATA_STORE_ID"# healthcare_project_id = "YOUR_HEALTHCARE_PROJECT_ID"# healthcare_location = "YOUR_HEALTHCARE_LOCATION"# healthcare_dataset_id = "YOUR_HEALTHCARE_DATASET_ID"# healthcare_fihr_store_id = "YOUR_HEALTHCARE_FHIR_STORE_ID"#  For more information, refer to:# https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_storeclient_options=(ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")iflocation!="global"elseNone)# Create a clientclient=discoveryengine.DocumentServiceClient(client_options=client_options)# The full resource name of the search engine branch.# e.g. projects/{project}/locations/{location}/dataStores/{data_store_id}/branches/{branch}parent=client.branch_path(project=project_id,location=location,data_store=data_store_id,branch="default_branch",)request=discoveryengine.ImportDocumentsRequest(parent=parent,fhir_store_source=discoveryengine.FhirStoreSource(fhir_store=client.fhir_store_path(healthcare_project_id,healthcare_location,healthcare_dataset_id,healthcare_fihr_store_id,),),# Options: `FULL`, `INCREMENTAL`reconciliation_mode=discoveryengine.ImportDocumentsRequest.ReconciliationMode.INCREMENTAL,)# Make the requestoperation=client.import_documents(request=request)print(f"Waiting for operation to complete:{operation.operation.name}")response=operation.result()# After the operation is complete,# get information from operation metadatametadata=discoveryengine.ImportDocumentsMetadata(operation.metadata)# Handle the responseprint(response)print(metadata)

Console

1. In the Google Cloud console, go to theAI Applications page.

   AI Applications

2. In the navigation menu, clickData Stores.

3. Clickadd_boxCreate data store.

4. In theSelect a data source pane, selectHealthcare API (FHIR) as your data source.
5. To import data from your FHIR store, do one of the following:
   • Select the FHIR store from the list of available FHIR stores:
     1. Expand theFHIR store field.
     2. In this list, select a dataset that resides in apermitted location and then select a FHIR store that uses FHIR version R4.
   • Enter the FHIR store manually:
     1. Expand theFHIR store field.
     2. ClickEnter FHIR store manually.
     3. In theFHIR store name dialog, enter the full name of the FHIR store in the following format:

        project/PROJECT_ID/locations/LOCATION/datasets/DATASET_ID/fhirStores/FHIR_STORE_ID

     4. ClickSave.
6. In theSynchronization section, select one of the following options.This selection cannot be changed after the data store is created.
   • One time: to perform a one-time batch data import. For further incremental imports, seeRefresh healthcare data.
   • Streaming: to perform a near real-time streaming data import. To stream data, you must create a data connector, which is a type of a data store. To set up a streaming data store using the REST API, contact your customer engineer.
7. In theWhat is the schema for this data? section, select one ofthese options:
   • Google predefined schema: to retain the Google-defined schema configurations, such as indexability, searchability, and retrievability, for the supported FHIR resources and elements. After you select this option, you cannot update the schema after you create the data store. If you want to be able to change the schema after the data store creation, select theCustom schema option.
     1. ClickContinue.
     2. In theYour data store name field, enter a name for your data store.
     3. ClickCreate.

     The data store you created is listed on theData Stores page.

   • Custom schema: to define your own schema configurations, such as indexability, searchability, and retrievability, for the supported FHIR resources and elements. To set up a configurable schema, contact your customer engineer.
     1. ClickContinue.
     2. Review the schema, expand each field, and edit the field settings.
     3. ClickAdd new fields to add new fields on the supported FHIR resources. You cannot remove the fields provided in the Google-defined schema.
     4. ClickContinue.
     5. In theYour data connector name field, enter a name for your data connector.
     6. ClickCreate.

     The data connector you created is listed on theData Stores page. The source FHIR store is added as an entity within the data connector.

8. ClickContinue.

REST

1. Create a data connector to set up streaming.

   curl -X POST \-H "Authorization: Bearer $(gcloud auth print-access-token)" \-H "Content-Type: application/json" \-H "X-Goog-User-Project:PROJECT_ID" \"https://us-discoveryengine.googleapis.com/v1alpha/projects/PROJECT_ID/locations/us:setUpDataConnector" \-d ' {  "collectionId": "COLLECTION_ID",  "collectionDisplayName": "COLLECTION_NAME",  "dataConnector": {  "dataSource": "gcp_fhir",  "params": {      "instance_uri": "projects/SOURCE_PROJECT_ID/locations/CLOUD_HEALTHCARE_DATASET_LOCATION/datasets/CLOUD_HEALTHCARE_DATASET_ID"    },    "entities": [      {        "entityName": "FHIR_STORE_NAME"        "healthcareFhirConfig": {          "enableConfigurableSchema":CONFIGURABLE_SCHEMA_TRUE|FALSE,          "enableStaticIndexingForBatchIngestion":STATIC_INDEXING_TRUE|FALSE        }      }    ],    "syncMode": "STREAMING"  }}'

   Replace the following:

   • PROJECT_ID: the ID of your Google Cloud project.
   • COLLECTION_ID: the ID of the collection to which you want to stream the FHIR R4 data.
   • COLLECTION_NAME: name of the collection to which you want to stream the FHIR R4 data.
   • SOURCE_PROJECT_ID: the ID of the Google Cloud project that contains the Cloud Healthcare API dataset and FHIR store.
   • CLOUD_HEALTHCARE_DATASET_ID: the ID of the Cloud Healthcare API dataset that contains the source FHIR store.
   • CLOUD_HEALTHCARE_DATASET_LOCATION: the location of the Cloud Healthcare API dataset that contains the source FHIR store.
   • FHIR_STORE_ID: the ID of the Cloud Healthcare API FHIR R4 store.
   • CONFIGURABLE_SCHEMA_TRUE|FALSE: a boolean when set totrue lets you configure the data store schema using theschema.update method.
   • STATIC_INDEXING_TRUE|FALSE: a boolean when set totrue let you import historical data with higher indexing quota. This is useful when you expect your search app to encounter higher data volume. However, individual records take longer to be indexed. Google strongly recommends that you set this field totrue.

   Response

   You should receive a JSON response similar to the following. If the valuefor thedone key istrue, it indicates that theoperation to create the data store was completed. Otherwise, the data storecreation operation was unsuccessful.

   {  "name": "OPERATION_ID",  "done": true,  "response": {    "@type": "type.googleapis.com/google.cloud.discoveryengine.v1main.DataConnector"  }}

   • If the collection is successfully created, a data connector is added tothe list of data stores ontheData Stores page in the Google Cloud console.
   • The created data connector contains an entity, which has the same name asthe FHIR R4 store from which you're streaming the data.

Console

1. In the Google Cloud console, go to theAI Applications page.

   AI Applications

2. In the navigation menu, clickData Stores.

   TheData Stores page displays a list of data stores in your Google Cloudproject with their details.

3. Verify whether the data store or the data connector that you created is inthe data stores list. In the data stores list, a data connector that streamsdata contains a data store that has the same name as the Cloud Healthcare APIFHIR store.

4. Select the data store or the data connector and verify its details.

   • For a data store:
     • The summary table lists the following details:
       • The data store ID, type, and region.
       • The number of documents indicating the number of FHIR resources imported.
       • The timestamp when the last document was imported.
       • Optionally, clickView details to see the document import details, suchas the details about a successful, partial, or failed import.
     • TheDocuments tab lists the resource IDs of the imported FHIR resourcesand their resource types in a paginated table. You can filter this table toverify whether a particular resource was imported.
     • TheActivity tab lists the document import details, such as the detailsabout a successful, partial, or failed import.
   • For a data connector:
     • The summary table lists the following details:
       • The collection ID, type, and region.
       • The name of the connected app.
       • The state of the connector, which is either active or paused.
     • TheEntities table shows the entity within the data connector.The entity's name is the source FHIR store name. The entity's ID isthe data connector's ID appended with the source FHIR store name.
       • Click the entity name to see its details. Because anentity is a data store instance within a data connector, theentity details are the same as a data store details.

5. In theSchema tab, view the properties for the supported FHIR resourcesand elements. ClickEdit to configure the schema.

REST

1. Verify the data store creation.

   curl -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" \ -H "Content-Type: application/json"\ -H "X-Goog-User-Project:PROJECT_ID" \ "https://us-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID"

   Replace the following:

   • PROJECT_ID: the ID of your Google Cloud project.
   • DATA_STORE_ID: the ID of the Vertex AI Search data store.

   Response

   You should receive a JSON response similar to the following. The responsecontains details of the created data store.

   {  "name": "projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID",  "displayName": "DATA_STORE_DISPLAY_NAME",  "industryVertical": "HEALTHCARE_FHIR",  "createTime": "DATA_STORE_CREATION_TIMESTAMP",  "solutionTypes": [    "SOLUTION_TYPE_SEARCH"  ],  "defaultSchemaId": "default_schema",  "documentProcessingConfig": {    "defaultParsingConfig": {      "ocrParsingConfig": {}    }  }}

2. Verify whether the FHIR data import operation is complete.

   curl -X GET \-H "Authorization: Bearer $(gcloud auth print-access-token)" \"https://us-discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/operations/IMPORT_OPERATION_ID"

   Replace the following:

   • PROJECT_ID: the ID of your Google Cloud project.
   • DATA_STORE_ID: the ID of the Vertex AI Search data store.
   • IMPORT_OPERATION_ID: the operation ID of the long-running operation that's returned when you call theimport method

   Response

   You should receive a JSON response similar to the following.The import operation is a long-running operation. While the operation isrunning, the response contains the following fields:

   • successCount: indicates the number of FHIR resources that were imported successfully so far.
   • failureCount: indicates the number of FHIR resources that failed to be imported so far. This field is displayed only if there are FHIR resources that failed to be imported.

   When the operation is complete, the response contains the following fields:

   • successCount: indicates the number of FHIR resources that were imported successfully.
   • failureCount: indicates the number of FHIR resources that failed to be imported. This field is displayed only if there are any FHIR resources that failed to be imported.
   • totalCount: indicates the number of FHIR resources that are present in the source FHIR store. This field is displayed only if there are any FHIR resources that failed to be imported.
   • done: has the valuetrue to indicate that the import operation is complete.
   • errorSamples: provides information about the resources that failed to be imported. This field is displayed only if there are any FHIR resources that failed to be imported.
   • errorConfig: provides a path to a Cloud Storage location that contains the error summary log file.

   { "name": "projects/PROJECT_ID/locations/us/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/operations/IMPORT_OPERATION_ID", "metadata": {   "@type": "type.googleapis.com/google.cloud.discoveryengine.v1.ImportDocumentsMetadata",   "createTime": "START_TIMESTAMP",   "updateTime": "END_TIMESTAMP",   "successCount": "SUCCESS_COUNT",   "failureCount": "FAILURE_COUNT",   "totalCount": "TOTAL_COUNT", }, "done": true, "response": {   "@type": "type.googleapis.com/google.cloud.discoveryengine.v1.ImportDocumentsResponse",  "errorSamples": [ERROR_SAMPLE],  "errorConfig": {     "gcsPrefix": "LOG_FILE_LOCATION"   } }}