OSGPT is a powerful plugin designed to dynamically load documents from specified folders and create searchable vector databases. Not only does it offer a quick way to query from your documents, but it also allows you to execute CLI commands on the host system, be it Linux/Unix or Windows.

Creates an endpoint to extract text content, images and document from different files format. Can be used in pyspark UDFs for bigdata retrieval.

FileCrawler is a versatile Python script for searching keywords across multiple file types in directory structures. It supports text files and PDFs, providing detailed search results with line/page numbers and word positions. Features colorized output and handles various file formats.