Update app.py

app.py

@@ -13,18 +13,18 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
 app = Flask(__name__)
-CORS(app)  # Enable CORS for frontend compatibility
+CORS(app)
 UPLOAD_FOLDER = os.path.join(os.getcwd(), 'uploads')
 PEGASUS_MODEL_DIR = 'fine_tuned_pegasus'
 BERT_MODEL_DIR = 'fine_tuned_bert'
 LEGALBERT_MODEL_DIR = 'fine_tuned_legalbert'
-MAX_FILE_SIZE = 100 * 1024 * 1024  # 100 MB limit
+MAX_FILE_SIZE = 100 * 1024 * 1024
 
 # Ensure upload folder exists
 if not os.path.exists(UPLOAD_FOLDER):
     os.makedirs(UPLOAD_FOLDER, exist_ok=True)
 
-transformers.logging.set_verbosity_error()  # Suppress transformers warnings
+transformers.logging.set_verbosity_error()
 os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1"
 
 # Pegasus Fine-Tuning
@@ -39,7 +39,7 @@ def load_or_finetune_pegasus():
         model = PegasusForConditionalGeneration.from_pretrained("google/pegasus-xsum")
         
         cnn_dm = load_dataset("cnn_dailymail", "3.0.0", split="train[:5000]")
-        xsum = load_dataset("xsum", split="train[:5000]")
+        xsum = load_dataset("xsum", split="train[:5000]", trust_remote_code=True)  # Added trust_remote_code=True
         combined_dataset = concatenate_datasets([cnn_dm, xsum])
         
         def preprocess_function(examples):
@@ -319,5 +319,5 @@ def summarize_document():
     return jsonify({"model_used": model, "summary": summary})
 
 if __name__ == '__main__':
-    port = int(os.environ.get("PORT", 5000))  # Use PORT env var if set by Hugging Face
+    port = int(os.environ.get("PORT", 5000))
     app.run(debug=False, host='0.0.0.0', port=port)