Update app.py

app.py

@@ -12,6 +12,11 @@ from tabulate import tabulate
 from sklearn.feature_extraction.text import TfidfVectorizer
 from multiprocessing import Pool, cpu_count
 from flask import Flask, request, jsonify
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 # Paths for saving artifacts
 MODEL_DIR = "./saved_models"
@@ -22,7 +27,16 @@ SKILL_TFIDF_PATH = os.path.join(MODEL_DIR, "skill_tfidf.pkl")
 QUESTION_ANSWER_PATH = os.path.join(MODEL_DIR, "question_to_answer.pkl")
 FAISS_INDEX_PATH = os.path.join(MODEL_DIR, "faiss_index.index")
 
-os.makedirs(MODEL_DIR, exist_ok=True)
+# Ensure the directory exists with error handling
+try:
+    os.makedirs(MODEL_DIR, exist_ok=True)
+    logger.info(f"Successfully created/accessed directory: {MODEL_DIR}")
+except PermissionError as e:
+    logger.error(f"Permission denied creating directory {MODEL_DIR}: {e}")
+    raise
+except Exception as e:
+    logger.error(f"Unexpected error creating directory {MODEL_DIR}: {e}")
+    raise
 
 # Load Datasets
 def load_dataset(file_path, required_columns=[]):
@@ -84,7 +98,7 @@ def initialize_resources(user_skills):
         answer_embeddings = universal_model.encode(list(question_to_answer.values()), convert_to_tensor=True, show_progress_bar=False).cpu().numpy()
         
         if not resources_valid(skill_tfidf.keys(), [s.lower() for s in user_skills]):
-            print("⚠ Saved skill TF-IDF mismatch detected. Recomputing resources.")
+            logger.info("⚠ Saved skill TF-IDF mismatch detected. Recomputing resources.")
             tfidf_vectorizer = TfidfVectorizer(stop_words='english')
             all_texts = user_skills + questions_df['Answer'].fillna("").tolist() + questions_df['Question'].tolist()
             tfidf_vectorizer.fit(all_texts)
@@ -113,7 +127,7 @@ def initialize_resources(user_skills):
         universal_model.save_pretrained(UNIVERSAL_MODEL_PATH)
         detector_model.save_pretrained(DETECTOR_MODEL_PATH)
         detector_tokenizer.save_pretrained(DETECTOR_MODEL_PATH)
-        print(f"Models and resources saved to {MODEL_DIR}")
+        logger.info(f"Models and resources saved to {MODEL_DIR}")
 
 # Evaluate Responses
 def evaluate_response(args):