Update app.py

app.py

@@ -4,34 +4,35 @@ import streamlit as st
 from typing import Generator
 from groq import Groq
 
+# Cargar variables de entorno
 _ = load_dotenv(find_dotenv())
-st.set_page_config(page_icon="📃", layout="wide", page_title="Groq & LLaMA3.1 Chat Bot...")
 
+# Configurar la página de Streamlit
+st.set_page_config(page_icon="📃", layout="wide", page_title="Groq & LLaMA3.1 Chat Bot...")
 
 def icon(emoji: str):
-    """Shows an emoji as a Notion-style page icon."""
+    """Muestra un emoji como ícono de página estilo Notion."""
     st.write(
         f'<span style="font-size: 78px; line-height: 1">{emoji}</span>',
         unsafe_allow_html=True,
     )
 
-
-# icon("⚡️")
-
+# Encabezado de la aplicación
 st.subheader("Groq Chat with LLaMA3.1 App", divider="rainbow", anchor=False)
 
+# Inicializar cliente Groq
 client = Groq(
     api_key=os.environ['GROQ_API_KEY'],
 )
 
-# Initialize chat history and selected model
+# Inicializar historial de chat y modelo seleccionado
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
 if "selected_model" not in st.session_state:
     st.session_state.selected_model = None
 
-# Define model details
+# Detalles de los modelos
 models = {
     "llama-3.1-70b-versatile": {"name": "LLaMA3.1-70b", "tokens": 4096, "developer": "Meta"},
     "llama-3.1-8b-instant": {"name": "LLaMA3.1-8b", "tokens": 4096, "developer": "Meta"},
@@ -46,16 +47,15 @@ models = {
     },
 }
 
-# Layout for model selection and max_tokens slider
-col1, col2 = st.columns([1, 3])  # Adjust the ratio to make the first column smaller
-
+# Diseño para la selección de modelo y slider de tokens
+col1, col2 = st.columns([1, 3])  # Ajusta la proporción para hacer la primera columna más pequeña
 
 with col1:
     model_option = st.selectbox(
         "Choose a model:",
         options=list(models.keys()),
         format_func=lambda x: models[x]["name"],
-        index=0,  # Default to the first model in the list
+        index=0,  # Predeterminado al primer modelo en la lista
     )
     max_tokens_range = models[model_option]["tokens"]
     max_tokens = st.slider(
@@ -67,36 +67,37 @@ with col1:
         help=f"Adjust the maximum number of tokens (words) for the model's response. Max for selected model: {max_tokens_range}",
     )
 
-# Detect model change and clear chat history if model has changed
+# Detectar cambio de modelo y limpiar historial de chat si el modelo ha cambiado
 if st.session_state.selected_model != model_option:
     st.session_state.messages = []
     st.session_state.selected_model = model_option
 
-# Add a "Clear Chat" button
+# Añadir un botón para "Limpiar Chat"
 if st.button("Clear Chat"):
     st.session_state.messages = []
-    
-# Display chat messages from history on app rerun
+
+# Mostrar mensajes de chat del historial en la aplicación
 for message in st.session_state.messages:
     avatar = "🔋" if message["role"] == "assistant" else "🧑‍💻"
     with st.chat_message(message["role"], avatar=avatar):
         st.markdown(message["content"])
 
-
 def generate_chat_responses(chat_completion) -> Generator[str, None, None]:
-    """Yield chat response content from the Groq API response."""
+    """Generar contenido de respuesta del chat a partir de la respuesta de la API de Groq."""
     for chunk in chat_completion:
         if chunk.choices[0].delta.content:
             yield chunk.choices[0].delta.content
 
-
-if prompt := st.chat_input("# Extract the benefits of the product, not the features. # You should be as brief as possible. # Omit the price, if any. # Do not mention the name of the product. # Use 3 paragraphs. # Try to synthesize or summarize. # Focus only on the benefits. # Highlight how this product helps the customer. # Always respond in Spanish. # The text you create will be used in an e-commerce product sales page through the Internet, so it must be persuasive, attractive, and above all very short and summarized. # Remember to keep the text short, summarized, synthesized in three paragraphs. # Surprise me with your best ideas! # Always answers in AMERICAN SPANISH. Stop after finish the first content genreated."):
+# Manejar la entrada del chat del usuario
+if prompt := st.chat_input(
+    "# Extract the benefits of the product, not the features. # You should be as brief as possible. # Omit the price, if any. # Do not mention the name of the product. # Use 3 paragraphs. # Try to synthesize or summarize. # Focus only on the benefits. # Highlight how this product helps the customer. # Always respond in Spanish. # The text you create will be used in an e-commerce product sales page through the Internet, so it must be persuasive, attractive, and above all very short and summarized. # Remember to keep the text short, summarized, synthesized in three paragraphs. # Surprise me with your best ideas! # Always answers in AMERICAN SPANISH. Stop after finish the first content genreated."
+):
     st.session_state.messages.append({"role": "user", "content": prompt})
 
     with st.chat_message("user", avatar="🧑‍💻"):  
         st.markdown(prompt)
 
-    # Fetch response from Groq API
+    # Obtener respuesta de la API de Groq
     try:
         chat_completion = client.chat.completions.create(
             model=model_option,
@@ -108,21 +109,21 @@ if prompt := st.chat_input("# Extract the benefits of the product, not the featu
             stream=True,
         )
 
-        # Use the generator function with st.write_stream
+        # Usar la función generadora con st.write_stream
         with st.chat_message("assistant", avatar="🔋"):
             chat_responses_generator = generate_chat_responses(chat_completion)
             full_response = st.write_stream(chat_responses_generator)
+
+        # Añadir la respuesta completa al historial de mensajes
+        if isinstance(full_response, str):
+            st.session_state.messages.append(
+                {"role": "assistant", "content": full_response}
+            )
+        else:
+            combined_response = "\n".join(str(item) for item in full_response)
+            st.session_state.messages.append(
+                {"role": "assistant", "content": combined_response}
+            )
+
     except Exception as e:
         st.error(e, icon="❌")
-
-    # Append the full response to session_state.messages
-    if isinstance(full_response, str):
-        st.session_state.messages.append(
-            {"role": "assistant", "content": full_response}
-        )
-    else:
-        # Handle the case where full_response is not a string
-        combined_response = "\n".join(str(item) for item in full_response)
-        st.session_state.messages.append(
-            {"role": "assistant", "content": combined_response}
-        )