nlpir-ingest-elasticsearch-plugin
An Ingest Plugin for Elasticsearch to extract text and format form Docx and PDF file
This project is for our own propose, but it was deprecated becase it will be slow when there are lots of files .
This project will open source with MIT license, you can use it with your own purpose. And we have a new project to do this with BETTER parsing result and new features like EXTRACT INFO from context. If you have a commercial needs for it please contect us .