Enhance DVC pull with retry logic and cache cleanup for improved reliability

.github/workflows/ci.yml

@@ -86,7 +86,33 @@ jobs:
 
     - name: Pull Models with DVC
       run: |
-        dvc pull models/random_forest_embedding_gridsearch.pkl models/label_names.pkl
+        # Clean any potentially corrupted cache
+        rm -rf .dvc/cache/files/md5/e1 || true
+        
+        # Retry logic for DVC pull to handle intermittent server errors
+        max_attempts=3
+        attempt=0
+        until [ $attempt -ge $max_attempts ]
+        do
+          dvc pull models/random_forest_embedding_gridsearch.pkl models/label_names.pkl && break
+          attempt=$((attempt+1))
+          echo "DVC pull attempt $attempt failed. Retrying in 10 seconds..."
+          # Clean cache on retry
+          rm -rf .dvc/cache || true
+          sleep 10
+        done
+        if [ $attempt -ge $max_attempts ]; then
+          echo "DVC pull failed after $max_attempts attempts"
+          exit 1
+        fi
+
+    - name: Verify Models Downloaded
+      run: |
+        if [ ! -f "models/random_forest_embedding_gridsearch.pkl" ] || [ ! -f "models/label_names.pkl" ]; then
+          echo "ERROR: Required model files not found after DVC pull"
+          exit 1
+        fi
+        echo "All required model files present"
 
     - name: Build Docker Image
       run: |