Document Extraction Python Packages

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.

lakshana

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

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.

docpick

Lightweight OCR + Local LLM → Schema-based Structured JSON Extraction

kreuzberg-cloud-sdk

Official Python client for the Kreuzberg Cloud document-processing API.

unpdf-markdown

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

iterationlayer

Official Python SDK for the Iteration Layer API

xberg-enterprise-sdk

Reserved name for the Xberg Enterprise SDK — official Python client for the Xberg Enterprise document extraction API. See https://github.com/xberg-io/sdks

pydoxtools

This library contains a set of tools in order to extract and synthesize structured information from documents

docuglean-ocr

An SDK for intelligent document processing using SOTA VLLM models

lumient-docstore

Persistent cache for LLM document extraction: extract once, query forever. CLI, Python API, and MCP server.

docuglean

An SDK for intelligent document processing using SOTA VLLM models