Add OCR Support for PDF and Image Files to Enhance System Usability

[IANTHEREAL]

To improve system usability and handle a broader range of document types, it is suggested to integrate OCR (Optical Character Recognition) capabilities. This enhancement will enable the system to process PDF files and images that do not contain embedded text but instead rely on scanned images or other visual formats.

Use Case:
A user uploads a PDF file that contains complicated structure (e.g., scanned documents). Currently, the system extracts 0 characters from such files, resulting in errors or failed processing steps like vector index construction. By integrating OCR, the system can extract meaningful text from these image-based files, allowing seamless processing.