Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import pandas as pd
-from transformers import BartForConditionalGeneration, TapexTokenizer, T5ForConditionalGeneration, T5Tokenizer
 from prophet import Prophet
+import openai
 
 # Abrindo e lendo o arquivo CSS
 with open("style.css", "r") as css:
@@ -26,39 +26,22 @@ html_content = f"""
 # Aplicar o markdown combinado no Streamlit
 st.markdown(html_content, unsafe_allow_html=True)
 
-# Cache models to prevent re-loading on every run
-#@st.cache_resource
-def load_translation_model(model_name):
-    return T5ForConditionalGeneration.from_pretrained(model_name)
+# Configurar a API do OpenRouter
+openai.api_base = "https://openrouter.ai/api/v1"
+openai.api_key = "<OPENROUTER_API_KEY>"
+openai.default_headers = {
+    "HTTP-Referer": "<https://huggingface.co/spaces/fschwartzer/streamlit_chatbot/>",  # Optional. Site URL for rankings on openrouter.ai.
+    "X-Title": "<Streamlit Chatbot>",  # Optional. Site title for rankings on openrouter.ai.
+}
 
-#@st.cache_resource
-def load_tapex_model():
-    return BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")
-
-#@st.cache_resource
-def load_tapex_tokenizer():
-    return TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq")
-
-pt_en_translator = load_translation_model("unicamp-dl/translation-pt-en-t5")
-en_pt_translator = load_translation_model("unicamp-dl/translation-en-pt-t5")
-tapex_model = load_tapex_model()
-tapex_tokenizer = load_tapex_tokenizer()
-tokenizer = T5Tokenizer.from_pretrained("unicamp-dl/translation-pt-en-t5")
-
-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
-
-# Function to translate and interact with TAPEX model
+# Function to interact with the model
 def response(user_question, all_anomalies):
-    question_en = translate(user_question, pt_en_translator, tokenizer, source_lang="pt", target_lang="en")
-    encoding = tapex_tokenizer(table=all_anomalies, 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
+    prompt = f"Considerando a seguinte tabela:\n{all_anomalies.to_string(index=False)}\nResponda a questão: {user_question}"
+    response = openai.ChatCompletion.create(
+        model="deepseek/deepseek-r1:free",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response.choices[0].message['content']
 
 # Load and preprocess the data
 def load_data(uploaded_file):
@@ -77,23 +60,23 @@ def preprocess_data(df):
         'Mai': '05', 'Jun': '06', 'Jul': '07', 'Ago': '08',
         'Set': '09', 'Out': '10', 'Nov': '11', 'Dez': '12'
     }
-    
+
     def convert_column_name(column_name):
         # Check if the column name is 'Rótulos de Linha'
         if column_name == 'Rótulos de Linha':
             return column_name
-    
+
         # Otherwise, proceed to convert
         parts = column_name.split('/')
         month = parts[0].strip()
         year = parts[1].strip()
-    
+
         # Clean year in case there are extra characters
         year = ''.join(filter(str.isdigit, year))
-    
+
         # Get month number from the dictionary
         month_number = month_dict.get(month, '00')  # Default '00' if month is not found
-    
+
         # Return formatted date string
         return f"{month_number}/{year}"
 
@@ -116,7 +99,7 @@ def apply_prophet(df_clean):
 
     # Criar um DataFrame vazio para armazenar todas as anomalias
     all_anomalies = pd.DataFrame()
-    
+
     # Processar cada linha no DataFrame
     for index, row in df_clean.iterrows():
         # Extract timestamp and value columns
@@ -188,16 +171,11 @@ with tab1:
     if uploaded_file:
         df = load_data(uploaded_file)
         df_clean = preprocess_data(df)
-        
+
         if df_clean.empty:
             st.warning("Não há dados válidos para processar.")
         else:
             # Cache the Prophet results
-            #if st.session_state['all_anomalies'].empty:
-                #with st.spinner('Aplicando modelo de série temporal...'):
-                    #all_anomalies = apply_prophet(df_clean)
-                    #st.session_state['all_anomalies'] = all_anomalies
-            # Cache the Prophet results
             if st.session_state['all_anomalies'].empty:
                 all_anomalies = apply_prophet(df_clean)
                 st.session_state['all_anomalies'] = all_anomalies
@@ -209,11 +187,11 @@ with tab2:
             bot_response = response(user_question, st.session_state['all_anomalies'])
             st.session_state['history'].append(('👤', user_question))
             st.session_state['history'].append(('🤖', bot_response))
-        
+
         for sender, message in st.session_state['history']:
             st.markdown(f"**{sender} {message}**")
-        
+
         if st.button("Limpar histórico"):
             st.session_state['history'] = []
     else:
-        st.warning("Por favor, processe os dados no Meta Prophet primeiro.")
+        st.warning("Por favor, processe os dados no Meta Prophet primeiro.")