Docling
Get your documents ready for gen AI
Docling scores 7.5/10 (Strong) in Crawl & Search.
Language Python License MIT Stars 62.6k★ Type library Self-host Yes Repo docling-project/docling Homepage https://docling-project.github.io/docling
Quality
Strong 7.5
Adoption 70
Activity 86
Maturity 90
Community 67
Capability 3
Show the math
Overall 7.5/10
value = 7.5/10
score = value
Adoption 7.3/10
value = 69.9/100
score = 1 + 9 * value / 100
Activity 8.8/10
value = 86.4/100
score = 1 + 9 * value / 100
Maturity 9.1/10
value = 90.4/100
score = 1 + 9 * value / 100
Community 7/10
value = 66.6/100
score = 1 + 9 * value / 100
Capability 1.2/10
value = 2.5/100
score = 1 + 9 * value / 100
Key metrics
62.6k★ GitHub stars
241/90d Recent commits
34 devs/90d Recent contributors
2.45 pages/s PDF conversion throughput (CPU, peak) Docling Technical Report (IBM Research, arXiv:2408.09869) performance table: peak 2.45 pages/s on Apple M3 Max 16-core (pypdfium backend, 16 threads); 1.57 pages/s on Intel Xeon E5-2690. Runs locally on commodity CPU. Source: https://arxiv.org/html/2408.09869v1
2y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
documents parsing pdf markdown rag