Update app.py

app.py

@@ -2,12 +2,12 @@ import pandas as pd
 import gradio as gr
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
 
-# Carregando o modelo e o tokenizador do GPT-2
+# Load the model and tokenizer for GPT-2
 tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
 model = GPT2LMHeadModel.from_pretrained('gpt2')
 
 df = pd.read_csv('anomalies.csv')
-df['Feedback'] = None
+df['Feedback'] = ""  # Initialize with empty strings instead of None for consistency
 
 # Preprocessing steps
 df['ds'] = pd.to_datetime(df['ds']).dt.strftime('%Y-%m-%d')  # Format the datetime values
@@ -20,12 +20,14 @@ def tokenize_row(row):
 # Apply the tokenization function to each row
 df['tokenized'] = df.apply(tokenize_row, axis=1)
 
-# Função para responder perguntas com GPT-2
+# Function to respond to questions with GPT-2
 def answer_question_with_gpt(question):
     if tokenizer.pad_token is None:
         tokenizer.pad_token = tokenizer.eos_token
 
-    prompt = f"Considering the follow: {df['tokenized']}. Question: {question} Resposta:"
+    # Simplify the prompt to avoid exceeding token limits
+    latest_entries = df['tokenized'].tail(10).tolist()  # Limit to the last 10 entries for context
+    prompt = f"Based on the following data: {' '.join(latest_entries)} Question: {question} Answer:"
     inputs = tokenizer(prompt, return_tensors='pt', padding='max_length', truncation=True, max_length=512)
     attention_mask = inputs['attention_mask']
     input_ids = inputs['input_ids']
@@ -33,42 +35,41 @@ def answer_question_with_gpt(question):
     generated_ids = model.generate(
         input_ids,
         attention_mask=attention_mask,
-        max_length=len(input_ids[0]) + 100,  # Aumentar o limite de geração
-        temperature=0.5,  # Ajustar a criatividade
-        top_p=0.9,  # Usar nucleus sampling
-        no_repeat_ngram_size=2  # Evitar repetições desnecessárias
+        max_length=len(input_ids[0]) + 100,
+        temperature=0.3,
+        top_p=0.9,
+        no_repeat_ngram_size=2
     )
     
     generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
-    # Processando para extrair apenas a resposta após "Resposta:"
-    response_part = generated_text.split("Resposta:")[1] if "Resposta:" in generated_text else "Resposta não encontrada."
-    # Limpeza adicional para remover qualquer texto indesejado após a resposta
-    final_response = response_part.split(".")[0] + "."  # Isso assume que a resposta termina na primeira sentença.
+    # Extract the response after "Answer:"
+    response_part = generated_text.split("Answer:")[1] if "Answer:" in generated_text else "No answer found."
+    final_response = response_part.split(".")[0] + "."
     return final_response
 
-# Função para adicionar feedback
-def add_feedback(nome, feedback):
+# Function to add feedback
+def add_feedback(name, feedback):
     global df
-    if grupo in df['Group'].values:
-        df.loc[df['Group'] == grupo, 'Feedback'] = feedback
-        return "Feedback adicionado com sucesso."
+    if name in df['Group'].values:
+        df.loc[df['Group'] == name, 'Feedback'] = feedback
+        return "Feedback successfully added."
     else:
-        return "Dado não encontrado no DataFrame."
+        return "Data not found in DataFrame."
 
 with gr.Blocks() as demo:
-    gr.Markdown("# Sistema de Consulta e Feedback de Dados")
+    gr.Markdown("# Data Query and Feedback System")
     with gr.Row():
         with gr.Column():
-            question_input = gr.Textbox(label="Faça uma Pergunta")
-            answer_output = gr.Textbox(label="Resposta", interactive=False)
-            ask_button = gr.Button("Perguntar")
+            question_input = gr.Textbox(label="Ask a Question")
+            answer_output = gr.Textbox(label="Answer", interactive=False)
+            ask_button = gr.Button("Ask")
         with gr.Column():
-            name_input = gr.Textbox(label="Nome para Feedback")
+            name_input = gr.Textbox(label="Name for Feedback")
             feedback_input = gr.Textbox(label="Feedback")
-            feedback_result = gr.Textbox(label="Resultado do Feedback", interactive=False)
-            submit_button = gr.Button("Enviar Feedback")
+            feedback_result = gr.Textbox(label="Feedback Result", interactive=False)
+            submit_button = gr.Button("Submit Feedback")
 
     ask_button.click(fn=answer_question_with_gpt, inputs=question_input, outputs=answer_output)
     submit_button.click(fn=add_feedback, inputs=[name_input, feedback_input], outputs=feedback_result)
 
-demo.launch()
+demo.launch()