Update app.py

app.py

@@ -8,6 +8,14 @@ from langchain.embeddings import HuggingFaceEmbeddings, SentenceTransformerEmbed
 from langchain.vectorstores import FAISS
 
 
+splitter = SentenceTransformersTokenTextSplitter(model_name='dangvantuan/sentence-camembert-large',
+    chunk_overlap=50
+    )
+embeddings_fun = HuggingFaceEmbeddings(model_name='dangvantuan/sentence-camembert-large')
+
+query = st.text_input("Entrer une question")
+
+st.text('La reponse à votre question:')
 
 def read_pdf(file):
     with tempfile.NamedTemporaryFile(delete=False) as temp:
@@ -20,24 +28,15 @@ st.title('PDF Text Extractor')
 
 uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
 if uploaded_file is not None:
-    raw_documents = read_pdf(uploaded_file)
-
-
-splitter = SentenceTransformersTokenTextSplitter(model_name='dangvantuan/sentence-camembert-large',
-chunk_overlap=50
-)
-
-documents = splitter.split_documents(raw_documents)
-
-
-embeddings_fun = HuggingFaceEmbeddings(model_name='dangvantuan/sentence-camembert-large')
-
-# embeddings_text = embeddings_fun.embed_documents(documents)
-
-faiss_db = FAISS.from_documents(documents, embeddings_fun)
-
-query = st.text_input("Entrer une question")
-docs = faiss_db.similarity_search(query)
-
-st.text('La reponse à votre question:')
-st.write(docs[0].page_content)
+    raw_documents = read_pdf(uploaded_file)    
+    documents = splitter.split_documents(raw_documents)
+    
+    # embeddings_text = embeddings_fun.embed_documents(documents)
+    
+    faiss_db = FAISS.from_documents(documents, embeddings_fun)
+    
+    docs = faiss_db.similarity_search(query)
+    
+    st.write(docs[0].page_content)
+else:
+    st.write("file not uploaded correctly")