Update app.py

app.py

@@ -9,7 +9,6 @@ from datetime import datetime
 
 from spacy.cli import download
 
-# Load or download the spaCy model
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
@@ -17,7 +16,6 @@ except OSError:
     download("en_core_web_sm")
     nlp = spacy.load("en_core_web_sm")
 
-# Load question generation model
 qg_model = AutoModelForSeq2SeqLM.from_pretrained("valhalla/t5-base-qa-qg-hl")
 qg_tokenizer = AutoTokenizer.from_pretrained("valhalla/t5-base-qa-qg-hl", use_fast=True)
 qg_pipeline = pipeline("text2text-generation", model=qg_model, tokenizer=qg_tokenizer)
@@ -84,20 +82,18 @@ def save_json_to_dataset(json_str):
             return "❌ HF_TOKEN not found in environment."
 
         repo_id = "UniversityAIChatbot/University_Inquiries_AI_Chatbot"
-        dataset_file = "dataset.json"
+        target_file = "database.json"
         local_dir = "hf_repo"
 
-        # ✅ Corrected clone_from
         repo = Repository(
             local_dir=local_dir,
-            clone_from=repo_id,  # << this is the fix
+            clone_from=repo_id,
             use_auth_token=hf_token,
-            repo_type="dataset"
         )
 
         repo.git_pull()
 
-        full_path = os.path.join(local_dir, dataset_file)
+        full_path = os.path.join(local_dir, target_file)
 
         if os.path.exists(full_path):
             with open(full_path, "r", encoding="utf-8") as f:
@@ -117,9 +113,9 @@ def save_json_to_dataset(json_str):
         with open(full_path, "w", encoding="utf-8") as f:
             json.dump(updated_data, f, indent=2, ensure_ascii=False)
 
-        repo.push_to_hub(commit_message="📥 Add new Q&A with timestamp")
+        repo.push_to_hub(commit_message="📥 Add new Q&A to database.json")
 
-        return "✅ Data with timestamp successfully pushed to HF dataset!"
+        return "✅ Data with timestamp successfully pushed to Space!"
     except Exception as e:
         return f"❌ Error: {str(e)}"