---
id: extend-ai
version: "1.18.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# extend-ai — Official Python SDK for Extend (extend.ai) — the document processing API. Parse, extract, classify, split, and edit PDFs and 35+ file types

License: permissive · Maintenance: active · Downloads: 183.2K/mo

## What it is and what it does

Extend-ai is the official Python SDK for Extend, a cloud-based document processing service. It provides typed, synchronous and asynchronous access to parse, extract structured data, classify, split, and edit documents in PDF and 35+ other file formats. The SDK wraps the Extend API with convenient methods that handle file upload, processing, and result retrieval in a single call.

The library integrates deeply with Pydantic, allowing you to define extraction schemas as typed models and get end-to-end validation from request to response. It includes polling helpers for production workflows, webhook verification utilities, and support for custom field types like ExtendDate, ExtendCurrency, and ExtendSignature. Synchronous methods have a 5-minute timeout and are suited for testing; production workloads should use polling or webhooks instead.

Use it for:

- Extract structured invoice data (line items, totals, dates) into typed Pydantic models for accounting systems.
- Classify incoming documents by type (invoice, receipt, contract) and route them to appropriate processing pipelines.
- Split multi-document PDF packets into individual documents for batch processing workflows.
- Parse unstructured PDFs into semantic chunks for document search and retrieval systems.
- Automate form filling and PDF editing via natural-language instructions.
- Build document processing workflows that chain extraction, classification, and splitting steps.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Official Python SDK for the Extend document processing API, enabling you to parse, extract, classify, split, and edit PDFs and 35+ file types via a few lines of code.

Yes. The SDK is actively maintained, has no known vulnerabilities, low install friction, and permissive licensing. It is well-suited for developers building document processing workflows who want typed, convenient access to the Extend API. Start with synchronous methods for prototyping; migrate to polling or webhooks for production workloads.

## Install

pip install extend-ai
uv add extend-ai
poetry add extend-ai

## Installing extend-ai

Before you install: Low friction install with four lightweight runtime dependencies (httpx, pydantic, pydantic-core, typing_extensions). Package is actively maintained with a recent release (4 days old) and no known vulnerabilities.

License in practice: MIT license is permissive, allowing commercial and private use with minimal restrictions—typical for open-source SDKs.

Quickstart:

pip install extend-ai

from extend_ai import Extend

client = Extend(token="YOUR_API_KEY")
result = client.parse(file={"url": "https://example.com/invoice.pdf"})
for chunk in result.output.chunks:
    print(chunk.content)

Requires Python 3.8 or later and a valid Extend API key.

Verify before relying:

- Whether the 5-minute timeout on synchronous methods is sufficient for typical production document sizes.
- Performance characteristics and latency for batch processing workflows.
- Exact coverage and accuracy of OCR across the 35+ supported file types.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 183.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

pdf parsing and extraction, document processing api, ocr and document ai, structured data extraction from documents, pdf classification and splitting, document workflow automation, typed document extraction, document-processing, pdf-extraction, api-client

[View on SkillFed](https://skillfed.io/packages/extend-ai) · [View on PyPI](https://pypi.org/project/extend-ai/)