Skip to main content

The official Python client for the DocumentExtractor API

Project description

DocumentExtractor.AI Python Client

A Python client for extracting structured data from documents using the DocumentExtractor API.
It provides convenient methods to upload documents, define extraction schemas, start extraction workflows, and retrieve structured results.


📦 Installation

pip install documentextractor

🚀 Quick Example

You can get started with just a few lines of code:

import os

from documentextractor import DocumentExtractorAPIClient, WorkflowCreate, SchemaCreate, RunCreate

api = DocumentExtractorAPIClient(
    api_key=os.environ.get("DOCUMENTEXTRACTOR_API_KEY"),
)

# Define a workflow and extraction schema
workflow = api.workflows.create(payload=WorkflowCreate(
    name="Simple Invoice Extraction",
    extraction_schema=SchemaCreate(
    name="Invoice Schema",
    description="Extract invoice number and total amount",
    is_array=False,
    children=[
        SchemaCreate(key="invoice_number", description="Sender-issued invoice number", type="Text", is_array=False),
        SchemaCreate(key="total_amount", description="Total amount payable, in original currency", type="Number", is_array=False),
    ],
),
))

# Upload a Document
file = api.files.upload("example_invoice.pdf")

# Trigger a run
results = await workflow.runs.create_and_wait_for_results(payload=RunCreate(file_ids=[file.id]))

# Get structured results
extracted_items = results.extracted_data.raw
print(f"Found {len(extracted_items)} extracted item(s).")
if extracted_items:
    # Pretty-print the structured data of the first result
    print(" - Data from first result:")
    import json
    print(json.dumps(extracted_items[0].data, indent=2))

For the best experience, however, it's recommended to get more familiar with the client. For a full end-to-end usage script, see examples/basic_usage.py.


📄 License

Copyright © 2025 Philipp Heller

Licensed under the Apache License 2.0. You may not use this file except in compliance with the License.

See the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

documentextractor-0.5.0.tar.gz (13.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

documentextractor-0.5.0-py3-none-any.whl (12.8 kB view details)

Uploaded Python 3

File details

Details for the file documentextractor-0.5.0.tar.gz.

File metadata

  • Download URL: documentextractor-0.5.0.tar.gz
  • Upload date:
  • Size: 13.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.8

File hashes

Hashes for documentextractor-0.5.0.tar.gz
Algorithm Hash digest
SHA256 457df35255a9c3177385293a7f4510de6005c604c28f401cf2e1d4aeab83735c
MD5 33f2fc8e211209b1a055a6a2c48172bc
BLAKE2b-256 2f0f78a482d91bba6c550146be095db0870fdffbd07010ffee40a72f8d8a719a

See more details on using hashes here.

File details

Details for the file documentextractor-0.5.0-py3-none-any.whl.

File metadata

File hashes

Hashes for documentextractor-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 51dbe781f0e4f9ec715928cd3ee74a6443a379c893fbef8828180c5c9d5c5e0a
MD5 4f502ca34940d63b5c682c1f540d8f73
BLAKE2b-256 ae7c538dbb662b96d03027264e9928c418acaddab5eb05e776992498e3967f3a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page