Update app.py

app.py

@@ -13,22 +13,25 @@ st.header("Pregunta al trebep")
 
 
 @st.cache_resource 
-def consultar():
+def read():
+    # CARGAMOS MODELO DE EMBEDDING
+    model_name = 'intfloat/multilingual-e5-base'
+    embedding = HuggingFaceEmbeddings(model_name=model_name)
+
+
+def setup():
     # CARGAMOS LLM
     os.environ["GROQ_API_KEY"] = "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"
     model = 'llama3-8b-8192'
     llm = ChatGroq(model = model)
     
-    # CARGAMOS MODELO DE EMBEDDING
-    model_name = 'intfloat/multilingual-e5-base'
-    embedding = HuggingFaceEmbeddings(model_name=model_name)
-    
     # CARGAMOS EL VECTORSTORE DE PINECONE
     os.environ["PINECONE_API_KEY"] ='4bf0b4cf-4ced-4f70-8977-d60bb8ae405a'
     index_name = "boe-intfloat-multilingual-e5-base"
     namespace = "trebep"
     vectorstore = PineconeVectorStore(index_name=index_name, namespace=namespace, embedding=embedding)
-    
+
+def ask()
     # CREAMOS EL RETRIEVAL
     qa = RetrievalQA.from_chain_type(
         llm=llm,
@@ -61,7 +64,9 @@ user_question = st.text_input("¡A jugar! Haz una pregunta al trebep:")
 if user_question:
 
     # Inicializar entorno
-    qa = consultar()
+    read()
+    setup()
+    qa = ask()
 
     # Obtenemos la respuesta
     respuesta = qa.invoke(user_question)