Update app.py

app.py

@@ -12,7 +12,6 @@ def extract_text(url):
     return text
 
 # Load Hugging Face model (for extracting named entities or QA)
-# Here we use a named entity recognition model, but you can use a question answering model if needed
 ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
 
 # Function to extract information using Hugging Face model
@@ -20,7 +19,7 @@ def extract_info_with_model(text):
     # Apply named entity recognition (NER) to extract entities from the text
     ner_results = ner_model(text)
 
-    # You can refine this based on the type of entity or information you want to extract
+    # Initialize variables
     keytags = []
     seller_name = ""
     location_details = ""
@@ -37,9 +36,8 @@ def extract_info_with_model(text):
             location_details = entity['word']  # Geopolitical entity as location
 
     # For amenities and facilities, you can modify the logic or use additional models (e.g., question-answering models)
-    # For now, we'll just return a placeholder for these
-    amenities = "No amenities found"
-    facilities = "No facilities found"
+    amenities = "No amenities found"  # Placeholder for the amenities
+    facilities = "No facilities found"  # Placeholder for the facilities
 
     return {
         "Keytags": ", ".join(keytags) if keytags else "No keytags found",
@@ -53,7 +51,18 @@ def extract_info_with_model(text):
 def get_info(url):
     text = extract_text(url)
     extracted_info = extract_info_with_model(text)
-    return extracted_info
+    
+    # Print debug to understand what's being returned
+    print(extracted_info)
+
+    # Ensure the information is returned in the expected format
+    return (
+        extracted_info["Keytags"],
+        extracted_info["Amenities"],
+        extracted_info["Facilities"],
+        extracted_info["Seller Name"],
+        extracted_info["Location Details"]
+    )
 
 # Gradio Interface to allow user input and display output
 demo = gr.Interface(