# Filimoa/open-parse

Improved file parsing for LLM’s

Repository: https://github.com/Filimoa/open-parse
Canonical: https://ross.abutalabs.com/products/open-parse
Homepage: https://filimoa.github.io/open-parse/
Language: Python
License: MIT
License Family: permissive
Topics: document-structure, table-detection, document-parser, layout-parsing
Last push: 2026-05-17T19:56:14+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 82, release rhythm 40, longevity 63
- inputs: {"age_days": 894, "days_push": 108, "days_rel": 659, "gap_med": 5, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3159, forks 143 (observed 2026-08-28T04:07:46.501981+00:00)

## What it is
Open Parse is a Python library that visually parses complex documents (primarily PDFs) into semantically meaningful chunks for LLM and RAG pipelines. It detects document layout, headings, and tables, and can cluster nodes using embeddings for higher-quality chunking.

## Use cases
- chunk pdfs for a rag pipeline
- extract tables from pdfs into markdown
- parse document layout with headings and sections
- split documents semantically instead of naive text splitting
- prepare complex documents as llm input
- convert pdf documents to markdown

## When to choose
- you need high-quality chunking of complex PDFs for RAG
- you need accurate table extraction into markdown
- you want visual layout-aware parsing rather than plain text splitting
- you want an open-source alternative to commercial document AI services

## When to avoid
- you only need simple plain-text splitting of flat text files
- you need OCR of scanned documents as a primary feature
- you need a hosted document-processing API with vendor support
- your documents are simple and a lightweight text splitter suffices

## Facets
- artifact type: library
- maturity: active
- function: parser, pdf, ocr, rag, nlp
- domain: pdf, large-language-models, developer-tools
- platform: python
- tags: document-chunking, layout-parsing, table-extraction, document-structure, pdf-parsing, semantic-chunking, natural-language-processing, retrieval-augmented-generation

## Member repositories
- Filimoa/open-parse (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:46.501981+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 2026-08-30T07:25:16.061594+00:00, confidence not recorded.
  - readme: https://github.com/Filimoa/open-parse (fetched 2026-08-28T04:07:46.501981+00:00, sha cddb3db0ce90)
  - homepage: https://filimoa.github.io/open-parse/ (fetched 2026-08-29T09:39:57.618013+00:00, sha ea86eb69d17b)
- Data as of 2026-08-30T08:39:29.467469+00:00.