Upload 2 files

app (1).py

@@ -0,0 +1,64 @@
+# -*- coding: utf-8 -*-
+"""app
+
+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
+from langchain.document_loaders import PyPDFLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+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")
+
+uploaded_file = st.file_uploader("Faça upload de um 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..."):
+        try:
+            loader = PyPDFLoader(pdf_path)
+            documents = loader.load()
+
+            text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+            docs = text_splitter.split_documents(documents)
+
+            embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+            vectorstore = FAISS.from_documents(docs, embeddings)
+
+            llm = ChatOpenAI(
+                openai_api_base="https://openrouter.ai/api/v1",
+                openai_api_key=os.environ["OPENROUTER_API_KEY"],
+                model='deepseek/deepseek-r1-zero:free'
+            )
+
+            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?"})
+
+            st.success("✅ Resposta gerada com sucesso!")
+            st.subheader("🤖 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]}...")
+
+        except Exception as e:
+            st.error(f"Erro ao processar o PDF: {str(e)}")

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+langchain
+openai
+python-dotenv
+PyPDF2
+faiss-cpu
+tiktoken
+pypdf
+sentence-transformers