docext
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
docext scores 4/10 (Emerging) in Data Extraction.
Language Python License Apache-2.0 Stars 2k★ Type library Self-host Yes Repo NanoNets/docext Homepage https://github.com/NanoNets/docext
Quality
Emerging 4.0
Adoption 33
Activity 11
Maturity 76
Community 31
Capability 50
Show the math
Overall 4/10
value = 4/10
score = value
Adoption 3.9/10
value = 32.7/100
score = 1 + 9 * value / 100
Activity 2/10
value = 11/100
score = 1 + 9 * value / 100
Maturity 7.8/10
value = 76.1/100
score = 1 + 9 * value / 100
Community 3.8/10
value = 30.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
2k★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
1.3y Project age
4mo ago 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.
vlm invoices tables structured on-prem