ドキュメントをデータストアにインポートする

構造化ドキュメントまたは非構造化ドキュメントをデータストアにインポートする。

もっと見る

このコードサンプルを含む詳細なドキュメントについては、以下をご覧ください。

コードサンプル

Python

詳細については、Vertex AI Agent Builder Python API のリファレンス ドキュメントをご覧ください。

Vertex AI Agent Builder に対する認証を行うには、アプリケーションのデフォルト認証情報を設定します。 詳細については、ローカル開発環境の認証の設定をご覧ください。



def import_documents_bigquery_sample(
    project_id: str,
    location: str,
    data_store_id: str,
    bigquery_dataset: str,
    bigquery_table: str,
) -> str:

    from google.api_core.client_options import ClientOptions
    from google.cloud import discoveryengine

    # 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"
    # bigquery_dataset = "YOUR_BIGQUERY_DATASET"
    # bigquery_table = "YOUR_BIGQUERY_TABLE"

    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = 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,
        bigquery_source=discoveryengine.BigQuerySource(
            project_id=project_id,
            dataset_id=bigquery_dataset,
            table_id=bigquery_table,
            data_schema="custom",
        ),
        # Options: `FULL`, `INCREMENTAL`
        reconciliation_mode=discoveryengine.ImportDocumentsRequest.ReconciliationMode.INCREMENTAL,
    )

    # Make the request
    operation = 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 metadata
    metadata = discoveryengine.ImportDocumentsMetadata(operation.metadata)

    # Handle the response
    print(response)
    print(metadata)

    return operation.operation.name


def import_documents_gcs_sample(
    project_id: str,
    location: str,
    data_store_id: str,
    gcs_uri: str,
) -> str:
    from google.api_core.client_options import ClientOptions
    from google.cloud import discoveryengine

    # 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"

    # Examples:
    # - Unstructured documents
    #   - `gs://bucket/directory/file.pdf`
    #   - `gs://bucket/directory/*.pdf`
    # - Unstructured documents with JSONL Metadata
    #   - `gs://bucket/directory/file.json`
    # - Unstructured documents with CSV Metadata
    #   - `gs://bucket/directory/file.csv`
    # gcs_uri = "YOUR_GCS_PATH"

    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = 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,
        gcs_source=discoveryengine.GcsSource(
            # Multiple URIs are supported
            input_uris=[gcs_uri],
            # Options:
            # - `content` - Unstructured documents (PDF, HTML, DOC, TXT, PPTX)
            # - `custom` - Unstructured documents with custom JSONL metadata
            # - `document` - Structured documents in the discoveryengine.Document format.
            # - `csv` - Unstructured documents with CSV metadata
            data_schema="content",
        ),
        # Options: `FULL`, `INCREMENTAL`
        reconciliation_mode=discoveryengine.ImportDocumentsRequest.ReconciliationMode.INCREMENTAL,
    )

    # Make the request
    operation = 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 metadata
    metadata = discoveryengine.ImportDocumentsMetadata(operation.metadata)

    # Handle the response
    print(response)
    print(metadata)

    return operation.operation.name

次のステップ

他の Google Cloud プロダクトに関連するコードサンプルの検索およびフィルタ検索を行うには、Google Cloud のサンプルをご覧ください。