Document Intelligence Python Packages

kreuzberg

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

infinity-parser2

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

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).

xberg-cli

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

contextgem

ContextGem: Effortless LLM extraction from documents

paddlenlp

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

crewai-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

langchain-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

llama-index-node-parser-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

llama-index-readers-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

surrealdb-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

txtai-xberg

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

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.

xberg-hermes-plugin

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.

pdf-strikethrough-detect

Detect struck-through (deleted) text in PDFs and scanned document images — vector/flag detection for born-digital PDFs, OCR + a tiny ONNX CNN for scans. No cloud calls.

contractex

Open-source Python library for legal document intelligence: privacy enforced in code, quality measured.

vera-mcp

Model Context Protocol integration for VERA archives

vera-doc

Embedded storage and search engine for portable .vera archives

vera-ingest

Source ingestion, chunking, and conversion adapters for VERA

vera-embed-openai

Official OpenAI embeddings provider for VERA

fast-tokenizer-python

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

vera-cli

Compatibility alias for the vera CLI; install `vera` instead