{"id":"docext","name":"docext","maker":"Nanonets","url":"https://github.com/NanoNets/docext","repo":"NanoNets/docext","package":"pypi:docext","summary":"An on-premise toolkit from Nanonets that pulls fields and tables from documents using vision-language models.","details":"It runs as a Python package with a web interface and uses locally served models. It is Apache licensed. The tool avoids sending documents to an outside service, since the models are hosted by the user.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/docext","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T20:20:00.691Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-03-17T09:41:55.000Z","latest_release":{"tag":"v0.1.14","published":"2025-06-30T06:28:52.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}