Import documents from Cloud Storage

Import documents from Cloud Storage

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Python

For more information, see the AI Applications Python API reference documentation.

To authenticate to AI Applications, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

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)

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.