Update app.py

app.py

@@ -1,9 +1,16 @@
 
-"""Document Q&A with Manual RAG - Hugging Face ZeroGPU."""
+"""
+Document Q&A with Manual RAG
+Hugging Face Spaces - CPU Compatible Version
+"""
 
 import os
-import spaces
 import traceback
+
+# Force CPU execution before loading ML libraries
+os.environ["CUDA_VISIBLE_DEVICES"] = ""
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
 import gradio as gr
 
 from rag_core import (
@@ -13,7 +20,6 @@ from rag_core import (
 )
 
 
-@spaces.GPU(duration=120)
 def respond(question, retrieval_only):
     """Retrieve evidence and optionally generate an answer."""
 
@@ -31,30 +37,34 @@ def respond(question, retrieval_only):
         )
 
         return (
-            result["answer"],
+            result.get("answer", "No answer generated."),
             display_evidence(result),
-            result["status"]
+            result.get("status", "Completed")
         )
 
     except (ValueError, RuntimeError) as error:
         traceback.print_exc()
+
         return (
-            str(error),
+            f"Error: {str(error)}",
             "",
             "Input or setup error"
         )
 
-    except Exception:
+    except Exception as error:
         traceback.print_exc()
+
         return (
             "Dataset/model access or generation failed. "
-            "Check the logs and try again.",
+            f"Details: {str(error)}",
             "",
             "Model error"
         )
 
 
 def make_demo():
+    """Create the Gradio interface."""
+
     return gr.Interface(
         fn=respond,
 
@@ -64,6 +74,7 @@ def make_demo():
                 placeholder="Which company produces the iPod?",
                 lines=2
             ),
+
             gr.Checkbox(
                 label="Retrieval only (skip answer generation)",
                 value=False
@@ -72,15 +83,18 @@ def make_demo():
 
         outputs=[
             gr.Textbox(
-                label="Answer - verify it against the evidence",
+                label="Answer - verify against evidence",
                 lines=5
             ),
+
             gr.Textbox(
                 label="Source passages and similarity scores",
                 lines=15
             ),
+
             gr.Textbox(
-                label="Run status"
+                label="Run status",
+                lines=2
             )
         ],
 
@@ -98,23 +112,36 @@ def make_demo():
             ["Which company produces the iPod?", False],
             ["At what age did Frédéric move to Paris?", False],
             ["What is Beyoncé's private mobile phone number?", False]
-        ]
+        ],
+
+        cache_examples=False,
+
+        flagging_mode="never"
     )
 
 
-if __name__ == "__main__":
+def main():
+    """Initialize retrieval system and launch the application."""
 
-    print("Initializing Document Q&A with Manual RAG...")
+    print("=" * 50)
+    print("Initializing Document Q&A with Manual RAG")
+    print("Execution mode: CPU")
+    print("=" * 50)
 
     try:
+        print("Loading retriever...")
+
         info = load_retriever()
-        print("Retriever initialized:", info)
+
+        print(f"Retriever initialized successfully: {info}")
 
     except Exception:
         print("Failed to initialize retriever.")
         traceback.print_exc()
         raise
 
+    print("Creating Gradio interface...")
+
     demo = make_demo()
 
     demo.queue(
@@ -122,6 +149,8 @@ if __name__ == "__main__":
         max_size=20
     )
 
+    print("Starting Gradio application...")
+
     demo.launch(
         server_name="0.0.0.0",
         server_port=int(os.environ.get("PORT", "7860")),
@@ -129,3 +158,7 @@ if __name__ == "__main__":
         show_error=True,
         ssr_mode=False
     )
+
+
+if __name__ == "__main__":
+    main()