Document Extraction Python Packages

unpdf-markdown

High-performance Rust PDF extraction library with Markdown/JSON output, CJK/RTL support, multi-column layout detection, and Python/.NET/CLI bindings.

hwpkit

Read, fill, and edit Korean HWP (Hancom Office) documents in Python. Extract text for LLM / RAG pipelines, fill government & university forms programmatically, and rewrite the binary without corrupting it.

agentic-doc

The official CLI for Agentic Document Extraction (ADE) by LandingAI — parse documents and extract schema-shaped data from your terminal

undoc

High-performance Rust library for extracting content from DOCX, XLSX, and PPTX into Markdown, plain text, or JSON with CJK support and .NET/Python bindings.

pageledger

Auditable page-level run ledger for OCR and document extraction

invoicedataextraction-sdk

Official Python SDK for Invoice Data Extraction. Uploads your files, submits the extraction, waits for it to finish and hands you the rows as data, or a spreadsheet, in a few lines of code.

platen-document

Standalone Python SDK for local PDF and document processing — OCR, text and structured extraction, Markdown, searchable PDFs, and PDF markup.

xberg-io-sdk

Official client SDKs (Python, TypeScript, Go) for the Xberg Enterprise and Xberg Pro document-processing APIs.

egyptian-national-id-ocr

Local, open-source OCR pipeline for Egyptian National ID cards — CLI, HTTP API, MCP server and Python SDK. No cloud APIs, nothing leaves your machine.

myocr-client

Official Python and Node.js SDKs for the myocr.app API: bank statements, invoices, receipts and tables from PDF, scans and photos to Excel or JSON

fastdocparse

Extract structured data from semi-structured documents using any OpenAI-compatible LLM, with per-field grounding and confidence.

pydoxtools

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

pyligent-agents

Governed AI agents for regulated financial document work. Harness, loop and graph, with evidence checks that make an extraction defensible.

kreuzberg-cloud-sdk

Official client SDKs (Python, TypeScript, Go) for the Xberg Enterprise and Xberg Pro document-processing APIs.

iterationlayer

Official Python SDK for the Iteration Layer API — document extraction, image transformation, image generation, document generation, and sheet generation.

paperpin

Pin every LLM-extracted value to the exact spot on the page it came from, and flag the values that aren't there at all. CPU-only, any model, zero telemetry.

lakshana

Zero-config schema discovery for document collections. Drop a folder of PDFs, get a JSON Schema.

multixtract

Vendor-neutral document extraction for search & RAG

evidence-check

Governed AI agents for regulated financial document work. Harness, loop and graph, with evidence checks that make an extraction defensible.

hirara

Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.

sacor

The Open Document Extraction Engine

hirarareader

Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.

hirara-web

Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.

hirara-core

Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.