Quickstart

pip install unstructured_sdk-*.whl

import time
import uuid

from unstructured import UnstructuredClient

# 1. Initialize the client (basic auth)
client = UnstructuredClient(
    base_url="https://unstructured.your-company.com/rest/unstructured",
    username="your-username",
    password="your-password",
)
# Alternatively, authenticate with an API token issued from the web UI:
#   client = UnstructuredClient(
#       base_url="https://unstructured.your-company.com/rest/unstructured",
#       api_token="your-api-token",
#       user_id="your-username",  # sent as the X-User-ID header
#   )

# 2. Create a data connector (S3 example)
connector = client.data_source.create(
    connector_name="my-s3-bucket",
    connector_body={
        "type": "S3DataSourceManager",
        "name": "my-s3-bucket",
        "bucket_name": "my-documents",
        "aws_access_key_id": "YOUR_ACCESS_KEY",
        "aws_secret_access_key": "YOUR_SECRET_KEY",
        "region": "us-east-1",
    },
)
print(f"✓ Created connector: {connector.profile_id}")

# 3. Define the tags you want to extract
for tag in [
    {
        "name": "document_type",
        "description": "Type of document (invoice, contract, report, etc.)",
        "output_type": "string",
        "available_values": ["invoice", "contract", "report", "other"],
    },
    {
        "name": "summary",
        "description": "A brief 2-3 sentence summary of the document",
        "output_type": "string",
    },
    {
        "name": "key_date",
        "description": "The most important date mentioned in the document",
        "output_type": "date",
    },
]:
    client.tags.upsert(tag_data=tag)
print("✓ Created tags: document_type, summary, key_date")

# 4. Extract metadata from all documents (runs as a background job)
job_id = str(uuid.uuid4())
client.metadata.generate.generate_batch(
    data_connector_name="my-s3-bucket",
    tag_names=["document_type", "summary", "key_date"],
    job_id=job_id,
)

while True:
    progress = client.task_status.get_status(job_id=job_id)
    print(f"  Classification {progress.percent_complete:.0f}% complete")
    if progress.status in ("completed", "failed", "aborted"):
        break
    time.sleep(10)

# 5. View the results
results = client.metadata.list(data_connector_name="my-s3-bucket")
for file_name, tags in results.metadata.items():
    print(f"\nFile: {file_name}")
    for tag_name, data in tags.items():
        if data.file_level:
            print(f"  {tag_name}: {data.file_level.values}")