Update main.py

main.py

@@ -10,27 +10,34 @@ import matplotlib.pyplot as plt
 import base64
 from io import BytesIO
 
-# Ensure Matplotlib and Transformers use writable cache directories
-os.environ["MPLCONFIGDIR"] = "/home/user/.cache/matplotlib"
-os.makedirs("/home/user/.cache/matplotlib", exist_ok=True)
+# Set writable cache directories within /tmp
+os.environ["HF_HOME"] = "/tmp/huggingface_cache"  # Replaces TRANSFORMERS_CACHE
+os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
+
+# Create directories if they don't exist
+os.makedirs(os.environ["HF_HOME"], exist_ok=True)
+os.makedirs(os.environ["MPLCONFIGDIR"], exist_ok=True)
 
 app = Flask(__name__)
 
 # Load Model from Local Directory
 MODEL_PATH = "bert_imdb_model.bin"
-TOKENIZER_PATH = "bert-base-uncased"  # Using default tokenizer from transformers
+TOKENIZER_PATH = "bert-base-uncased"
 
 if os.path.exists(MODEL_PATH):
     print("Loading model from local file...")
     model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
     model.load_state_dict(torch.load(MODEL_PATH, map_location=torch.device('cpu')))
 else:
-    print(f"Error: Model file {MODEL_PATH} not found. Make sure it's in the same directory.")
+    print(f"Error: Model file {MODEL_PATH} not found.")
     exit(1)
 
 model.eval()
 tokenizer = BertTokenizer.from_pretrained(TOKENIZER_PATH)
 
+# ... rest of your code (keep the rest unchanged) ...
+
+
 def predict_sentiment(text):
     tokens = tokenizer.encode(text, add_special_tokens=True)
     chunks = [tokens[i:i + 512] for i in range(0, len(tokens), 512)]