Update app.py

app.py

@@ -1,42 +1,67 @@
 import torch
 import gradio as gr
-
-# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-
+# Use a pipeline as a high-level helper
 question_answer = pipeline("question-answering",
-                           model="deepset/roberta-base-squad2")
-
-# question_answer = pipeline("question-answering",
-#                            model=model_path)
+                         model="deepset/roberta-base-squad2")
 
 def read_file_content(file_obj):
     """
     Reads the content of a file object and returns it.
+    Attempts multiple encodings if the default fails.
+    
     Parameters:
     file_obj (file object): The file object to read from.
     Returns:
     str: The content of the file.
     """
-    try:
-        with open(file_obj.name, 'r', encoding='utf-8') as file:
-            context = file.read()
-            return context
-    except Exception as e:
-        return f"An error occurred: {e}"
-
-#
+    encodings = ['utf-8', 'latin-1', 'cp1252', 'ascii']
+    
+    for encoding in encodings:
+        try:
+            with open(file_obj.name, 'r', encoding=encoding) as file:
+                context = file.read()
+                return context
+        except UnicodeDecodeError:
+            continue
+        except Exception as e:
+            return f"An error occurred: {e}"
+    
+    return "Error: Unable to read the file with any supported encoding"
 
 def get_answer(file, question):
+    if file is None:
+        return "Please upload a file"
+    if not question:
+        return "Please enter a question"
+        
     context = read_file_content(file)
-    answer = question_answer(question=question, context=context)
-    return answer["answer"]
+    if context.startswith("An error occurred") or context.startswith("Error:"):
+        return context
+        
+    try:
+        answer = question_answer(question=question, context=context)
+        return answer["answer"]
+    except Exception as e:
+        return f"Error processing question: {str(e)}"
 
-demo = gr.Interface(fn=get_answer,
-                    inputs=[gr.File(label="Upload your file(.txt)"), gr.Textbox(label="Input your question",lines=1)],
-                    outputs=[gr.Textbox(label="Answer text",lines=2)],
-                    title="Document_Question_And_Answer Chatbot",
-                    description="THIS APPLICATION WILL BE USED TO ANSER QUESTIONS BASED ON CONTEXT PROVIDED.")
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=get_answer,
+    inputs=[
+        gr.File(label="Upload your file (.txt)", type="file"),
+        gr.Textbox(label="Input your question", lines=1, placeholder="Enter your question here...")
+    ],
+    outputs=[
+        gr.Textbox(label="Answer", lines=2)
+    ],
+    title="Document Question & Answer Chatbot",
+    description="Upload a text document and ask questions about its content. The AI will find relevant answers from the text.",
+    examples=[
+        ["sample.txt", "What is the main topic?"]
+    ]
+)
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()