# chatdoc-com/OCRFlux

OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.

Repository: https://github.com/chatdoc-com/OCRFlux
Canonical: https://ross.abutalabs.com/products/ocrflux
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-04-14T08:28:45+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 77, release rhythm 35, longevity 32
- inputs: {"age_days": 455, "days_push": 141, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2533, forks 155 (observed 2026-08-28T04:06:59.018746+00:00)

## What it is
OCRFlux is a Python toolkit built on a 3B-parameter vision-language model that converts PDFs and images into clean Markdown, handling complex layouts, tables, equations, and cross-page content merging. It ships with released model weights and benchmark datasets, and can run on a single consumer GPU like a GTX 3090.

## Use cases
- convert pdf documents to markdown
- extract tables from pdfs
- parse multi-column pdf layouts
- merge tables that span multiple pages
- ocr scanned documents into readable text
- prepare pdfs for llm ingestion
- run document parsing on a single gpu

## When to choose
- you need high-quality pdf-to-markdown conversion with complex layouts or tables
- you need cross-page table or paragraph merging
- you want to run document parsing locally on a consumer GPU
- you need both English and Chinese document parsing

## When to avoid
- you only need simple text extraction from plain digital PDFs
- you have no GPU available
- you need a lightweight CPU-only OCR solution
- you need real-time or very high-throughput processing

## Facets
- artifact type: library
- maturity: active
- function: ocr, pdf, machine-learning, llm-inference, parser
- domain: pdf, machine-learning, developer-tools
- platform: python, cross-platform
- tags: pdf-to-markdown, vision-language-model, document-parsing, table-extraction, multimodal, natural-language-processing, gpu, linux

## Member repositories
- chatdoc-com/OCRFlux (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:59.018746+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:16.023521+00:00, confidence not recorded.
  - readme: https://github.com/chatdoc-com/OCRFlux (fetched 2026-08-28T04:06:59.018746+00:00, sha 25ccd881df10)
- Data as of 2026-08-30T08:39:29.467469+00:00.