Add explicit HF_TOKEN support for Hugging Face Spaces

README.md

@@ -70,6 +70,10 @@ python app.py
 - Educational tool for medical students
 - Research tool for studying correlation between visual findings and written reports
 
+## Environment Variables
+
+- **HF_TOKEN** (optional): Hugging Face token for accessing private models or improved rate limits. If not set, the system will use public models without authentication.
+
 ## Note
 
 This system is designed as a support tool and should not replace professional medical diagnosis. Always consult with healthcare professionals for medical decisions. 

mediSync/models/image_analyzer.py

@@ -35,9 +35,15 @@ class XRayImageAnalyzer:
         self.logger.info(f"Using device: {self.device}")
 
         # Load model and feature extractor
+        # Use HF_TOKEN from environment if available (for Hugging Face Spaces)
+        hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN")
         try:
-            self.feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
-            self.model = AutoModelForImageClassification.from_pretrained(model_name)
+            self.feature_extractor = AutoFeatureExtractor.from_pretrained(
+                model_name, token=hf_token
+            )
+            self.model = AutoModelForImageClassification.from_pretrained(
+                model_name, token=hf_token
+            )
             self.model.to(self.device)
             self.model.eval()  # Set to evaluation mode
             self.logger.info(f"Successfully loaded model: {model_name}")

mediSync/models/text_analyzer.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import re
 
 import torch
@@ -40,6 +41,9 @@ class MedicalReportAnalyzer:
 
         self.logger.info(f"Using device: {self.device}")
 
+        # Use HF_TOKEN from environment if available (for Hugging Face Spaces)
+        hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGING_FACE_HUB_TOKEN")
+
         # Load NER model for entity extraction
         try:
             self.ner_pipeline = pipeline(
@@ -47,6 +51,7 @@ class MedicalReportAnalyzer:
                 model=ner_model,
                 aggregation_strategy="simple",
                 device=0 if self.device == "cuda" else -1,
+                token=hf_token,
             )
             self.logger.info(f"Successfully loaded NER model: {ner_model}")
         except Exception as e:
@@ -55,9 +60,11 @@ class MedicalReportAnalyzer:
 
         # Load classifier model for severity assessment
         try:
-            self.tokenizer = AutoTokenizer.from_pretrained(classifier_model)
+            self.tokenizer = AutoTokenizer.from_pretrained(
+                classifier_model, token=hf_token
+            )
             self.classifier = AutoModelForSequenceClassification.from_pretrained(
-                classifier_model
+                classifier_model, token=hf_token
             )
             self.classifier.to(self.device)
             self.classifier.eval()