# docling-project/docling

> Docling is a document parsing library for many formats (PDF, DOCX, PPTX, XLSX, HTML, EPUB, audio, video) with advanced PDF understanding: page layout, tables, formulas, OCR. It prepares structured data for generative AI and RAG pipelines.

- Magnitude: 2.3 out of 10 — Cooling
- Stars: 68,294 total · +7 stars on 2026-10-02 (UTC), ≈ 28 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2024-07-09 · Last push: 2026-10-02
- GitHub: https://github.com/docling-project/docling · Homepage: https://docling-project.github.io/docling · Page: https://gitnova.dev/en/r/docling-project/docling

## Useful for

- Convert a PDF paper to Markdown for a RAG pipeline
- Extract tables and structure from scanned PDFs via OCR
- Plug document parsing into LangChain or LlamaIndex via built-in integrations

## Why it’s here

- 7 stars so far today, about 28 expected by the end of the day.
- Interest is fading: the two-day pace is 28% of the previous week and a half.
- About 12 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4,983
- Issues and pull requests: 3,966
- Watchers: 229
- Average over the last week: 53 per day
- Usual pace: 117 per day
- Latest release: v2.132.0 (2026-10-01)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-19 5.1, 09-20 7.0, 09-21 5.8, 09-22 3.5, 09-23 3.0, 09-24 3.6, 09-25 3.6, 09-26 2.6, 09-27 2.5, 09-28 2.6, 09-29 2.5, 09-30 2.4, 10-01 2.4, 10-02 2.4

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-02 10:18 UTC, updated every 30 minutes.