Update app.py

app.py

@@ -44,10 +44,14 @@ from langchain_community.document_loaders import PDFMinerLoader
 from langchain_text_splitters import NLTKTextSplitter
 from langchain_google_genai import GoogleGenerativeAIEmbeddings 
 from langchain_community.vectorstores import Chroma  
+from langchain_core.runnables import RunnablePassthrough
+
+
 
 uploaded_file = st.file_uploader("Choose a pdf file",type = "pdf")
 
 if uploaded_file is not None:
+    
     pdf_file = io.BytesIO(uploaded_file.read())
     pdf_loader = PDFMinerLoader(pdf_file)
     dat_nik = pdf_loader.load()
@@ -63,6 +67,24 @@ if uploaded_file is not None:
     db_connection = Chroma(persist_directory="./chroma_db_", embedding_function=embedding_model)
 
     retriever = db_connection.as_retriever(search_kwargs={"k": 5})
+
+    def format_docs(docs):
+        return "\n\n".join(doc.page_content for doc in docs)
+
+    rag_chain = (
+        {"context": retriever | format_docs, "question": RunnablePassthrough()}
+        | chat_template
+        | chat_model
+        | output_parser
+    )
+
+    user_input = st.text_area("Ask Questions to AI")
+    if st.button("Submit"):
+        st.subheader(":green[Query:]")
+        st.subheader(user_input)
+        response = rag_chain.invoke(user_input)
+        st.subheader(":green[Response:-]")
+        st.write(response)
     
 # dat = PDFMinerLoader("2404.07143.pdf")
 # dat_nik =dat.load()
@@ -86,23 +108,5 @@ if uploaded_file is not None:
 
 
 
-from langchain_core.runnables import RunnablePassthrough #takes user's question.
-
-def format_docs(docs):
-    return "\n\n".join(doc.page_content for doc in docs)
-
-# format chunks: takes the 5 results, combines all the chunks and displays one output.
-rag_chain = (
-    {"context": retriever | format_docs, "question": RunnablePassthrough()}
-    | chat_template
-    | chat_model
-    | output_parser
-)
+ #takes user's question.
 
-user_input = st.text_area("Ask Questions to AI")
-if st.button("Submit"):
-    st.subheader(":green[Query:]")
-    st.subheader(user_input)
-    response = rag_chain.invoke(user_input)
-    st.subheader(":green[Response:-]")
-    st.write(response)