Document Ai Python Packages

haiku-rag-slim

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

haiku-rag

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

exstruct

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.

deepdoctection

A Repo For Document AI

asset-aware-mcp

Agent document collaboration: versioned PDF pages/annotations/forms, raster frames, DOCX/PPTX, spreadsheets and CSV/TSV, with checked edits, source provenance, CSL citations and wikilink evidence libraries

puffinparse

One API for every document parser: parse, OCR and extract across 18 providers, with an open, inspectable benchmark.

parse-bench

ParseBench - A Document Parsing Benchmark for AI Agents

fieldproof

Document extraction that shows its work: every LLM-extracted field grounded to its source words, verified, and reviewable.

assay-server

Behavioral regression testing for AI apps and agents: pytest plugin, behavior diff, CI gate, and document extraction metrics

pageledger

Auditable page-level run ledger for OCR and document extraction

assay-evals

Behavioral regression testing for AI apps and agents: pytest plugin, behavior diff, CI gate, and document extraction metrics

thepipe-api

Get clean data from tricky documents, powered by vision-language models ⚡

dd-core

A Repo For Document AI

docket-idp

Invoice and receipt OCR for Python: extract cited, validated data with local or hosted LLMs

ocracy

Facade to many implementations of (OCR) image-to-text-characters engines

mdify-cli

MDify is a document-to-Markdown conversion library for extracting structured content from complex PDFs and document images, including tables, charts, and scanned documents.

pdfmux

PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

dd-datasets

A Repo For Document AI

documentor-ai

An AI-powered documentation suite that semantically parses your codebase and generates stunning, interactive docs via CLI, Web UI, and CI/CD.

xberg-io-sdk

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

optical-context-mcp

MCP server that compresses OCR-heavy PDFs into dense packed images so AI agents can handle long visual documents

py-idp

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema discovery, HITL review, prod FastAPI server. AGPL-3.0 + commercial.

locale-invoice-check

Matched-pair EN/DE/ES invoice extraction regression harness with deterministic CI gates

vera-mcp

Model Context Protocol integration for VERA archives