Update app.py

app.py

@@ -1,13 +1,13 @@
 import torch
 import gradio as gr
 
+# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-pipe = pipeline(
+question_answer = pipeline(
     "question-answering", 
     model="deepset/roberta-base-squad2")
 
-# Function to read the content of a file object
 def read_file_content(file_obj):
     """
     Reads the content of a file object and returns it.
@@ -22,29 +22,14 @@ def read_file_content(file_obj):
             return context
     except Exception as e:
         return f"An error occurred: {e}"
-
-# Function to get the answer to a question from a file
+    
 def get_answer(file, question):
-    """
-    Answers a question based on the content of a file.
-    Parameters:
-    file (file object): The file object containing the context.
-    question (str): The question to answer.
-    Returns:
-    str: The answer to the question.
-    """
-    if not question or not file:
-        return "Please provide both a question and a file."
     context = read_file_content(file)
-    answer = pipe(question=question, context=context)
+    answer = question_answer(question=question, context=context)
     return answer["answer"]
 
-# Create the Gradio interface
-demo = gr.Interface(fn=get_answer,
-                    inputs=[gr.File(label="File Upload"), gr.Textbox(label="Prompt Input", lines=1)],
-                    outputs=[gr.Textbox(label="Response", lines=1)],
-                    title="@caesar-2series: Rag Application",
-                    description="Retrieval Augmented Generation Questions-Answering Application")
-
-# Launch the Gradio interface
+demo = gr.Interface(fn=get_answer, inputs=[gr.File(label="File Upload"), gr.Textbox(label="Prompt Input", lines=1)],
+                     outputs=[gr.Textbox(label="Response", lines=1)],
+                     title="@caesar-2series: Rag Application",
+                     description="Retrieval Augmented Generation Questions-Answering Application")
 demo.launch()