✨ feat(additional-formats): use docling-project/docling to convert pdf and csv to md for indexing

[KemingHe]

🎯 Problem

Current indexing only source from .md and .rst files for simplicity, discarding valuable information in .pdf and .csv and other file types.

💡 Proposed Solution

For unified internal interface, convert all to .md using docling-project/docling while retaining metadata before indexing. This allows future-proof file type support, even for code files and others.

🤔 Alternatives Considered

Considered low level approaches such as using pdfplumber, determined too complex given existing integrated solutions such as docling.