diff --git a/app.py b/app.py
index e161eb3..d1038f7 100644
--- a/app.py
+++ b/app.py
@@ -1,8 +1,8 @@
+# import os
+# from dotenv import load_dotenv
+# from langchain_community.chat_models import ChatOpenAI
 import streamlit as st
-import os
-from dotenv import load_dotenv
-from langchain_community.chat_models import ChatOpenAI
-from chats.streamlit_tools import import_file, clear_cache
+from chats.streamlit_tools import import_file  # ,clear_cache
 from streamlit_extras.add_vertical_space import add_vertical_space
 from langchain_tools.pdf_tools import PdfLangChain
 from langchain_tools.lc_tools import LangChainTools
@@ -14,31 +14,27 @@ st.set_page_config(page_title="LLMOneClusterTeam")
 
 # sidebar
 with st.sidebar:
-
     # Cargar el logo (asegúrate de que el archivo de imagen esté en la misma carpeta que tu script)
     logo_path = "documents/Logo azulblanco.png"
-    # Ajusta el ancho según sea necesario
     logo = st.sidebar.image(logo_path, width=200)
 
-    add_vertical_space(24)
+    # Ajusta el ancho según sea necesario
+    add_vertical_space(28)
     # pdf_name = import_file()
+    st.markdown("Built by [OneCluster](https://www.onecluster.org/).")
 
-    # Crea un botón en Streamlit que llama a la función clear_cache() cuando se presiona
-    if st.button('Eliminar caché'):
-        clear_cache()
-    if st.button('Reiniciar'):
-        st.experimental_rerun()
-    st.markdown(
-        "Built by [OneCluster](https://www.onecluster.org/)."
+
+col1, col2 = st.columns([1.1, 1])
+with col1:
+    st.title(
+        "DocumentAssist",
     )
-
-st.title('💬📄 LLM CHat APP')
+with col2:
+    logo_2 = st.image("documents/pdfs/logo_1-removebg-preview.png", width=110)
 
 pdf_name = import_file()
 if pdf_name:
-
     with st.spinner("Processing the document..."):
-
         # Inicializamos la clase PdfLangChain
         pdfLangChain = PdfLangChain(pdf_name)
         pdf_name = pdfLangChain.file_name
@@ -57,9 +53,8 @@ if pdf_name:
 
         # Creamos el vector store
         docstorage = langChainTools.create_vector_strore(
-            docs_split,
-            pdf_name,
-            embedding_model)
+            docs_split, pdf_name, embedding_model
+        )
 
     # Cargamos el modelo LLM desde LangChain
     llm = langChainTools.load_llm_openai()
@@ -67,9 +62,8 @@ if pdf_name:
     # Creamos la cadena que integra Vectorstroe, el LLM para hacer consultas.
     # Para este caso la cadena tene el parametro de memoria.
     qa = langChainTools.define_retrieval_qa_memory(
-        llm, docstorage,
-        pdf_name,
-        embedding_model)
+        llm, docstorage, pdf_name, embedding_model
+    )
 
     # Store conversation history
     if "messages" not in st.session_state.keys():
@@ -95,7 +89,7 @@ if pdf_name:
 
     st.sidebar.button("Clear chat history", on_click=clear_chat_history)
 
-    @ st.cache_resource
+    @st.cache_resource
     def get_num_tokens(prompt):
         """Get the number of tokens in a given prompt"""
         return len(prompt.split())
@@ -111,32 +105,28 @@ if pdf_name:
         # Generate a new response if last message is not from assistant
         if st.session_state.messages[-1]["role"] != "assistant":
             with st.spinner("Thinking..."):
-
                 # Creamos la cadena que integra Vectorstroe, el LLM para hacer consultas.
                 # Para este caso la cadena tene el parametro de memoria.
                 qa = langChainTools.define_retrieval_qa_memory(
-                    llm, docstorage,
-                    pdf_name,
-                    embedding_model)
+                    llm, docstorage, pdf_name, embedding_model
+                )
 
-                input = "\n".join([msg["content"]
-                                   for msg in st.session_state.messages])
+                input = "\n".join([msg["content"] for msg in st.session_state.messages])
 
-                query = qa.invoke({"question": f"{prompt}"},
-                                  return_only_outputs=True)
+                query = qa.invoke({"question": f"{prompt}"}, return_only_outputs=True)
 
                 response_text = query["answer"]
                 documents_source = query["source_documents"]
 
                 messageManager = MessageManager()
 
-                citation: str = messageManager.generate_citations(
-                    documents_source)
+                citation: str = messageManager.generate_citations(documents_source)
                 # st.markdown(citation)
 
             with st.chat_message("assistant"):
                 st.write(response_text)
                 st.session_state.messages.append(
-                    {"role": "assistant", "content": response_text})
+                    {"role": "assistant", "content": response_text}
+                )
                 expander = st.expander("Fuentes")
                 expander.markdown(citation)
diff --git a/chats/__pycache__/chat_tools.cpython-311.pyc b/chats/__pycache__/chat_tools.cpython-311.pyc
index 82c7cc3..6fe77b5 100644
Binary files a/chats/__pycache__/chat_tools.cpython-311.pyc and b/chats/__pycache__/chat_tools.cpython-311.pyc differ
diff --git a/documents/pdfs/logo_1-removebg-preview.png b/documents/pdfs/logo_1-removebg-preview.png
new file mode 100644
index 0000000..8e14692
Binary files /dev/null and b/documents/pdfs/logo_1-removebg-preview.png differ
diff --git a/documents/pdfs/logo_1.jpeg b/documents/pdfs/logo_1.jpeg
new file mode 100644
index 0000000..403a0b5
Binary files /dev/null and b/documents/pdfs/logo_1.jpeg differ