Update app.py

app.py

@@ -50,7 +50,6 @@ def create_prompt(top_k_list: list[dict], question: str) -> str:
 
     {question}'''
 
-"""Gradio Application"""
 def process_files(ground_truth_file, pdf_files):
     # Process ground truth file
     if ground_truth_file.name.endswith('.csv'):
@@ -108,44 +107,21 @@ def process_files(ground_truth_file, pdf_files):
         }
     ]
 
-def query_llm(question):
-
-    # Add OpenAI response column
+     # Add OpenAI response column
     queries_t['response'] = openai.chat_completions(
         model='gpt-4-0125-preview', messages=messages
     )
+    
     queries_t['answer'] = queries_t.response.choices[0].message.content
 
-    return "Files processed successfully!"
-
-    # Perform top-k lookup
-    context = chunks_t.top_k(question).collect()
-
-    # Create prompt
-    prompt = create_prompt(context, question)
-
-    # Prepare messages for OpenAI
-    messages = [
-        {
-            'role': 'system',
-            'content': 'Please read the following passages and answer the question based on their contents.'
-        },
-        {
-            'role': 'user',
-            'content': prompt
-        }
-    ]
-
-    # Get LLM response
-    response = openai.chat_completions(model='gpt-4-0125-preview', messages=messages)
-    answer = response.choices[0].message.content
+    df_output = queries_t.select(queries_t.Question, queries_t.correct_answer, queries_t.answer).collect().to_pandas()
 
-    # Add new row to queries_t
-    new_row = {'Question': question, 'answer': answer}
-    queries_t.insert([new_row])
+    try:
+    #Display content
+      return df_output
 
-    # Return updated dataframe
-    return queries_t.select(queries_t.Question, queries_t.answer).collect()
+    except Exception as e:
+        return f"An error occurred: {str(e)}", None
 
 # Gradio interface
 with gr.Blocks() as demo:
@@ -156,15 +132,14 @@ with gr.Blocks() as demo:
         pdf_files = gr.File(label="Upload PDF Documents", file_count="multiple")
 
     process_button = gr.Button("Process Files")
-    process_output = gr.Textbox(label="Processing Output")
 
-    question_input = gr.Textbox(label="Enter your question")
-    query_button = gr.Button("Query LLM")
+    df_output = gr.DataFrame(label="Pixeltable Table")
 
-    output_dataframe = gr.Dataframe(label="LLM Outputs")
+    #question_input = gr.Textbox(label="Enter your question")
+    #query_button = gr.Button("Query LLM")
 
-    process_button.click(process_files, inputs=[ground_truth_file, pdf_files], outputs=process_output)
-    query_button.click(query_llm, inputs=question_input, outputs=output_dataframe)
+    process_button.click(process_files, inputs=[ground_truth_file, pdf_files], outputs=df_output)
+    #query_button.click(query_llm, inputs=question_input, outputs=output_dataframe)
 
 if __name__ == "__main__":
     demo.launch()