Handle Edge Case When Corpus is Empty

[Shehrozkashif]

📌 Background / Context

The pipeline currently crashes or behaves unexpectedly if data/processed/corpus.txt is empty or missing. Proper handling improves robustness and user experience.

🎯 Objectives

• Gracefully handle missing or empty corpus
• Provide clear error messages
• Reduce setup issues for new users

✅ Tasks

• Check if corpus file exists
• Validate corpus is not empty
• Add descriptive error messages and instructions
• Provide guidance in README or setup scripts