Update app.py

app.py

@@ -6,7 +6,6 @@ Automatically generated by Colab.
 Original file is located at
     https://colab.research.google.com/drive/1ZybFOpX1r-SAA-RslP5WJkQ9gdI6JCCj
 """
-
 import streamlit as st
 import os
 from langchain.chat_models import ChatOpenAI
@@ -17,48 +16,55 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chains import RetrievalQA
 import tempfile
 
-st.set_page_config(page_title="Análise de PDF com LangChain", layout="centered")
-st.title("📄🔍 Análise de PDF com LangChain")
+st.set_page_config(page_title="Chat com PDF", layout="centered")
+st.title("📄 Chat com PDF usando LangChain")
 
-uploaded_file = st.file_uploader("Faça upload de um PDF", type="pdf")
+uploaded_file = st.file_uploader("📤 Envie um arquivo PDF", type="pdf")
 
 if uploaded_file is not None:
     with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
         tmp.write(uploaded_file.read())
         pdf_path = tmp.name
 
-    with st.spinner("Processando o PDF..."):
+    with st.spinner("🔍 Processando o PDF..."):
         try:
+            # Carregar e dividir o PDF
             loader = PyPDFLoader(pdf_path)
             documents = loader.load()
 
             text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
             docs = text_splitter.split_documents(documents)
 
+            # Gerar embeddings
             embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
             vectorstore = FAISS.from_documents(docs, embeddings)
 
+            # Criar modelo LLM
             llm = ChatOpenAI(
                 openai_api_base="https://openrouter.ai/api/v1",
                 openai_api_key=os.environ["OPENROUTER_API_KEY"],
                 model='deepseek/deepseek-r1-zero:free'
             )
 
+            # Criar a cadeia de QA
             qa_chain = RetrievalQA.from_chain_type(
                 llm=llm,
                 retriever=vectorstore.as_retriever(),
                 return_source_documents=True
             )
 
-            resposta = qa_chain.invoke({"query": "Qual é o principal assunto tratado neste PDF?"})
+            # Interface para pergunta
+            pergunta = st.text_input("❓ Faça uma pergunta sobre o PDF:")
+
+            if pergunta:
+                resposta = qa_chain.invoke({"query": pergunta})
 
-            st.success("✅ Resposta gerada com sucesso!")
-            st.subheader("🤖 Resposta:")
-            st.write(resposta['result'])
+                st.success("✅ Resposta:")
+                st.write(resposta['result'])
 
-            st.subheader("📄 Fontes:")
-            for i, doc in enumerate(resposta['source_documents']):
-                st.markdown(f"**Fonte {i+1}:**\n\n{doc.page_content[:500]}...")
+                with st.expander("📄 Fontes usadas"):
+                    for i, doc in enumerate(resposta['source_documents']):
+                        st.markdown(f"**Fonte {i+1}:**\n\n{doc.page_content[:500]}...")
 
         except Exception as e:
-            st.error(f"Erro ao processar o PDF: {str(e)}")
+            st.error(f"Erro: {str(e)}")