Re-upload valid PDFs with Git LFS

orchestrator.py

@@ -41,10 +41,13 @@ VECTOR_STORE_DIR = os.getenv('VECTOR_STORE_DIR', '/tmp/vector_store')
 # Allow disabling RAG entirely for resource-constrained environments
 DISABLE_RAG = os.getenv('DISABLE_RAG', 'false').lower() in ('true', '1', 'yes')
 
-# Set cache directories for model loading (must match Dockerfile)
-os.environ.setdefault('TRANSFORMERS_CACHE', '/app/.cache/huggingface')
-os.environ.setdefault('HF_HOME', '/app/.cache/huggingface')
-os.environ.setdefault('SENTENCE_TRANSFORMERS_HOME', '/app/.cache/sentence-transformers')
+
+import os
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface_cache"
+os.environ["SENTENCE_TRANSFORMERS_HOME"] = "/tmp/huggingface_cache"
+os.environ["HF_HOME"] = "/tmp/huggingface_cache"
+os.makedirs("/tmp/huggingface_cache", exist_ok=True)
+
 
 # Pre-download embedding model to cache
 def _ensure_embedding_model_cached(model_name: str) -> bool: