Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 import os
-from langchain_community.embeddings import HuggingFaceEmbeddings  # Using Hugging Face embeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain_groq import ChatGroq
 from langchain.chains.question_answering import load_qa_chain
@@ -31,7 +31,7 @@ def get_text_chunks(text):
 
 def get_vector_store(text_chunks):
     """Creates and saves a FAISS vector store from text chunks."""
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Using Hugging Face embeddings
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     vector_store.save_local("faiss_index")
 
@@ -52,22 +52,21 @@ def get_conversational_chain():
 
     model = ChatGroq(
         temperature=0.3,
-        model_name="deepseek-r1-distill-llama-70b",  # Using Mixtral model through Groq
+        model_name="deepseek-r1-distill-llama-70b",
         groq_api_key=os.getenv("GROQ_API_KEY")
     )
     prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
     return chain
-    
+
 def eliminar_texto_entre_tags(texto):
     patron = r'<think>.*?</think>'
-    texto_limpio = re.sub(patron, '', texto)
+    texto_limpio = re.sub(patron, '', texto, flags=re.DOTALL)
     return texto_limpio
 
-
 def user_input(user_question):
     """Handles user queries by retrieving answers from the vector store."""
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Using Hugging Face embeddings
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
     new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     docs = new_db.similarity_search(user_question)
@@ -109,7 +108,8 @@ def main():
 
     st.sidebar.header("Upload & Process PDF Files")
     st.sidebar.markdown(
-        "Using DeepSeek R1 model for advanced conversational capabilities.")
+        "Using DeepSeek R1 model for advanced conversational capabilities."
+    )
 
     with st.sidebar:
         pdf_docs = st.file_uploader(