superdoc-sdk

library1.14.0pypypi✓ verified 85d ago

SuperDoc SDK (CLI-backed) is a Python library for document parsing and data extraction, focusing on structured outputs from PDFs and images. It provides both high-level and low-level APIs for interacting with SuperDoc's cloud service. Current version 1.14.0, released monthly (requires Python >=3.9).

ai-ml devops

pip install superdoc-sdk

INSTALL

IMPORT

SIG · SUPERDOC-SDK

superdoc-sdk

ai-mlpythonv1.14.0

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

SuperDocClient

✓ from superdoc import SuperDocClient

✗ from superdoc_sdk import SuperDocClient

AsyncSuperDocClient

✓ from superdoc import AsyncSuperDocClient

✗ from superdoc_sdk import AsyncSuperDocClient

SuperDocDocument

✓ from superdoc import SuperDocDocument

✗ from superdoc_sdk import SuperDocDocument

Initialize client with API key and parse a PDF document.

import os from superdoc_sdk import SuperDocClient client = SuperDocClient(api_key=os.environ.get('SUPERDOC_API_KEY', '')) # Parse a PDF with open('document.pdf', 'rb') as f: result = client.parse_document(f, file_type='pdf') print(result.id) print(result.status)

Debug

Known issues

breakingThe import path changed from `superdoc.client` to `superdoc_sdk` in v1.12. Code using the old path will break.

fix

Update imports: `from superdoc_sdk import SuperDocClient`.

affects: >=1.12.0

breaking`parse_document` now requires `file_type` as a mandatory keyword argument (previously inferred from extension). Omitting it raises a `ValueError`.

fix

Always specify `file_type` (e.g., 'pdf', 'image', 'docx').

affects: >=1.13.0

gotchaThe library uses a CLI-backed architecture; ensure the `superdoc` CLI is installed and available in PATH during init, or the SDK may fail silently.

fix

Install the CLI via `pip install superdoc-cli` or add its location to PATH.

affects: all

deprecatedMethod `document.parse()` was deprecated in v1.14 in favor of `document.extract()`. Old method will be removed in v2.0.

fix

Replace `doc.parse()` with `doc.extract()`.

affects: >=1.14.0

gotchaAPI key must be provided via environment variable `SUPERDOC_API_KEY` or passed explicitly to the constructor. If neither is set, the client raises a `ConfigurationError`.

fix

Set `SUPERDOC_API_KEY` in environment or pass `api_key` parameter.

affects: all

gotchaThe library uses `httpx` for async requests; by default, the client is sync. Mixing sync and async contexts can cause `RuntimeError`.

fix

Use `async with SuperDocClient(...) as client:` for async operations.

affects: all

breakingResponse model `DocParseResponse` had field `status` renamed from `state` in v1.10. Old code accessing `result.state` will fail.

fix

Access `result.status` instead of `result.state`.

affects: >=1.10.0

Upgrade

Version history

1.14.0latest on PyPI · released Jun 1, 2026

Audit

Dependencies

httpxrequiredHTTP client for API requests

pydanticrequiredData validation and settings management

python-multipartrequiredFile uploads via multipart

Agent activity

17 hits · last 30 days

node

OpenAI (training)

Resources

No resource links recorded.