aws-samples / bedrock-claude-chat

AWS-native chatbot using Bedrock + Claude (+Mistral)
MIT No Attribution
693 stars 237 forks source link

Fix: PDF Text Extraction Fails with Character Corruption #414

Closed statefb closed 3 days ago

statefb commented 3 days ago

Issue #, if available: close #413

Description of changes: Download NLTK in advance while Docker building process to avoid on-demand download (NLTK is used in partition method in unstructured module)

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.