Update rag.py

rag.py

@@ -1,7 +1,7 @@
 import json
 from sentence_transformers import SentenceTransformer, util
 from groq import Groq
-import datetime
+from datetime import datetime
 import requests
 from io import BytesIO
 from PIL import Image, ImageDraw, ImageFont
@@ -23,9 +23,15 @@ similarity_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
 HF_DATASET_REPO = "midrees2806/unmatched_queries"  # Your dataset repo
 HF_TOKEN = os.getenv("HF_TOKEN")  # From Space secrets
 
-# Load dataset (automatically using the path)
-with open('dataset.json', 'r') as f:
-    dataset = json.load(f)
+# --- Dataset Loading ---
+try:
+    with open('dataset.json', 'r') as f:
+        dataset = json.load(f)
+    if not all(isinstance(item, dict) and 'input' in item and 'response' in item for item in dataset):
+        raise ValueError("Invalid dataset structure")
+except Exception as e:
+    print(f"Error loading dataset: {e}")
+    dataset = []
 
 # Precompute embeddings
 dataset_questions = [item.get("input", "").lower().strip() for item in dataset]