Update app.py

app.py

@@ -23,11 +23,11 @@ html_content = f"""
         <div style='width: 20px; height: 40px; background-color: green; margin-right: 1px;'></div>
         <div style='width: 20px; height: 40px; background-color: red; margin-right: 1px;'></div>
         <div style='width: 20px; height: 40px; background-color: yellow; margin-right: 20px;'></div>
-        <span style='font-size: 50px; font-weight: normal; font-family: "Kanit", sans-serif;'><strong>PROTAX</strong></span>
+        <span style='font-size: 50px; font-weight: normal; font-family: "Kanit", sans-serif;'><strong>NOSTRADAMUS</strong></span>
     </div>
     <div style='text-align: left; width: 100%;'>
         <span style='font-size: 20px; font-weight: normal; color: #333; font-family: "Kanit", sans-serif'>
-        <strong>PRO</strong>phet & <strong>TA</strong>pex e<strong>X</strong>plorer</span>
+        Meta Prophet + Microsoft TAPEX</span>
     </div>
 </div>
 """
@@ -115,55 +115,55 @@ if uploaded_file:
             all_anomalies.sort_values(by=['monetary value'], ascending=False, inplace=True)
             all_anomalies = all_anomalies.fillna('').astype(str)
             st.session_state['all_anomalies'] = all_anomalies
-
-    # Load translation models
-    pt_en_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-pt-en-t5")
-    en_pt_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-en-pt-t5")
-    tokenizer = T5Tokenizer.from_pretrained("unicamp-dl/translation-pt-en-t5")
-
-    # Load TAPEX model
-    tapex_model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")
-    tapex_tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq")
-
-    def translate(text, model, tokenizer, source_lang="pt", target_lang="en"):
-        input_ids = tokenizer.encode(text, return_tensors="pt", add_special_tokens=True)
-        outputs = model.generate(input_ids)
-        translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return translated_text
-
-    def response(user_question, table_data):
-        question_en = translate(user_question, pt_en_translator, tokenizer, source_lang="pt", target_lang="en")
-        encoding = tapex_tokenizer(table=table_data, query=[question_en], padding=True, return_tensors="pt", truncation=True)
-        outputs = tapex_model.generate(**encoding)
-        response_en = tapex_tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
-        response_pt = translate(response_en, en_pt_translator, tokenizer, source_lang="en", target_lang="pt")
-        return response_pt
-
-    # Streamlit interface
-    st.dataframe(st.session_state['all_anomalies'].head())
-
-    # Chat history
-    if 'history' not in st.session_state:
-        st.session_state['history'] = []
-
-    user_question = st.text_input("Escreva sua questão aqui:", "")
-
-    if user_question:
-        st.session_state['history'].append(('👤', user_question))
-        st.markdown(f"**👤 {user_question}**")
-        
-        bot_response = response(user_question, st.session_state['all_anomalies'])
-        
-        st.session_state['history'].append(('🤖', bot_response))
-        st.markdown(f"<div style='text-align: right'>**🤖 {bot_response}**</div>", unsafe_allow_html=True)
-
-    if st.button("Limpar"):
-        st.session_state['history'] = []
-
-    for sender, message in st.session_state['history']:
-        if sender == '👤':
-            st.markdown(f"**👤 {message}**")
-        elif sender == '🤖':
-            st.markdown(f"<div style='text-align: right'>**🤖 {message}**</div>", unsafe_allow_html=True)
 else:
     st.warning("Por favor, carregue um arquivo CSV ou XLSX para começar.")
+
+# Load translation models
+pt_en_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-pt-en-t5")
+en_pt_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-en-pt-t5")
+tokenizer = T5Tokenizer.from_pretrained("unicamp-dl/translation-pt-en-t5")
+
+# Load TAPEX model
+tapex_model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")
+tapex_tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq")
+
+def translate(text, model, tokenizer, source_lang="pt", target_lang="en"):
+    input_ids = tokenizer.encode(text, return_tensors="pt", add_special_tokens=True)
+    outputs = model.generate(input_ids)
+    translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return translated_text
+
+def response(user_question, table_data):
+    question_en = translate(user_question, pt_en_translator, tokenizer, source_lang="pt", target_lang="en")
+    encoding = tapex_tokenizer(table=table_data, query=[question_en], padding=True, return_tensors="pt", truncation=True)
+    outputs = tapex_model.generate(**encoding)
+    response_en = tapex_tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+    response_pt = translate(response_en, en_pt_translator, tokenizer, source_lang="en", target_lang="pt")
+    return response_pt
+
+# Streamlit interface
+st.dataframe(st.session_state['all_anomalies'].head())
+
+# Chat history
+if 'history' not in st.session_state:
+    st.session_state['history'] = []
+
+user_question = st.text_input("Escreva sua questão aqui:", "")
+
+if user_question:
+    st.session_state['history'].append(('👤', user_question))
+    st.markdown(f"**👤 {user_question}**")
+    
+    bot_response = response(user_question, st.session_state['all_anomalies'])
+    
+    st.session_state['history'].append(('🤖', bot_response))
+    st.markdown(f"<div style='text-align: right'>**🤖 {bot_response}**</div>", unsafe_allow_html=True)
+
+if st.button("Limpar"):
+    st.session_state['history'] = []
+
+for sender, message in st.session_state['history']:
+    if sender == '👤':
+        st.markdown(f"**👤 {message}**")
+    elif sender == '🤖':
+        st.markdown(f"<div style='text-align: right'>**🤖 {message}**</div>", unsafe_allow_html=True)