reverting frontend

app.py

@@ -68,33 +68,17 @@ def process_faq(question, user_id="anonymous", model="claude-sonnet"):
         print(f"DEBUG: Sending to {lambda_url}")
         print(f"DEBUG: Payload: {json.dumps(payload, indent=2)}")
         
-        # Make the API call with streaming
-        with requests.post(
+        # Make the API call
+        response = requests.post(
             lambda_url,
             headers={"Content-Type": "application/json"},
-            json=payload,
-            stream=True
-        ) as response:
-            if response.status_code != 200:
-                return f"Error: Lambda function returned status code {response.status_code}"
-            
-            # Process the streaming response
-            full_response = ""
-            for chunk in response.iter_content(chunk_size=1024, decode_unicode=True):
-                if chunk:
-                    try:
-                        # Try to parse the chunk as JSON
-                        chunk_data = json.loads(chunk)
-                        if "response" in chunk_data:
-                            chunk_text = chunk_data["response"]
-                            full_response += chunk_text
-                            yield full_response
-                    except json.JSONDecodeError:
-                        # If not JSON, treat as plain text
-                        full_response += chunk
-                        yield full_response
-            
-            return full_response
+            json=payload
+        )
+        
+        if response.status_code != 200:
+            return f"Error: Lambda function returned status code {response.status_code}"
+        
+        return response.text
             
     except Exception as e:
         return f"Error processing FAQ: {str(e)}"
@@ -143,11 +127,7 @@ def execute_elasticsearch_query(query_body):
 
 # --- Gradio v4.x UI ---
 def faq_wrapper(question, user_id, model):
-    # Gradio expects a non-generator for Interface
-    result = ""
-    for chunk in process_faq(question, user_id, model):
-        result = chunk
-    return result
+    return process_faq(question, user_id, model)
 
 def elasticsearch_generate(natural_input):
     return natural_to_query(natural_input)