Extractor is an HTTP service used to convert PDF, Markdown, HTML, Docx, Xlsx, CSV and other files into plain text output. It is used in RAG implementation to read external documents for vectorization.

Demo: https://extractor.gulu.ai

The access speed may be slow. It is for trial use only and should not be used in production.

Start the application server using Docker

docker run -d --restart=always --name extractor \
     -p 8080:80 \
     mylxsw/extractor:1.0.0

Convert PDF document to plain text

curl -s -X POST http:https://127.0.0.1:8080/v1/extractor/file -F file=@'test.pdf'

Automatically download the document of the URL and convert it to plain text

curl -s -X POST http:https://127.0.0.1:8080/v1/extractor/url -d 'url=https://example.com/test.pdf'

MIT

Copyright (c) 2024,mylxsw