Document Intelligence Python Packages

kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

paddlenlp

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

contextgem

ContextGem: Effortless LLM extraction from documents

tool-helpers

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

fast-dataindex

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

preocr

Fast document classification and OCR detection. Analyzes any file type to determine if OCR is needed, saving time and money on unnecessary processing.

vectorless

Knowing by reasoning, not vectors.

ks-xlsx-parser

XLSX parser for LLMs, RAG, LangChain, LangGraph, CrewAI, Claude, MCP — turns Excel (.xlsx) into citation-ready JSON with formulas, charts, dependency graphs, and token-counted chunks. Open-source Python library (MIT).

infinity-parser2

INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document intelligence.

longparser

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.

fast-tokenizer-python

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

faster-tokenizer

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

llama-index-readers-kreuzberg

LlamaIndex reader and node parser integrations for kreuzberg — 88+ format document extraction with element-aware splitting

langchain-kreuzberg

Langchain document loader for Kreuzberg

knwler

Knwler is a lightweight, single-file Python tool that extracts structured knowledge graphs from documents using AI. Feed it a PDF or text file and receive a richly connected network of entities, relationships, and topics — complete with an interactive HTML report and exports ready for your favorite graph analytics platform.

decompose-mcp

The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

faster-tokenizers

PaddleNLP Faster Tokenizer Library written in C++

llama-index-node-parser-kreuzberg

LlamaIndex reader and node parser integrations for kreuzberg — 88+ format document extraction with element-aware splitting

paddle-pipelines

Paddle-Pipelines: An End to End Natural Language Proceessing Development Kit Based on PaddleNLP

mseep-kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

document-intelligence-mcp

Local document intelligence MCP server — extract text, tables, metadata from PDF and DOCX. No API key needed.

kreuzberg-txtai

Kreuzberg integration for txtai — drop-in Textractor replacement and custom pipeline

kreuzberg-crewai

Extract text and metadata from 88+ document formats — PDF, DOCX, XLSX, HTML, images with OCR, and more — directly from your CrewAI agents.