Update app.py

app.py

@@ -70,7 +70,6 @@ def chunk_text(text: str, max_chunk_size: int = 1000) :
 
     return chunks
 
-
 # Streamlit UI
 st.title("CUDA Documentation QA System")
 
@@ -110,11 +109,12 @@ if query and st.session_state.documents_loaded:
         # Create a PromptTemplate for the QA chain
         qa_prompt = PromptTemplate(template="Answer the following question based on the context provided:\n\n{context}\n\nQuestion: {question}\nAnswer:", input_variables=["context", "question"])
 
-        # Create the retrieval QA chain
-        qa_chain = RetrievalQA(
+        # Load the QA chain
+        qa_chain = load_qa_chain(
+            prompt=qa_prompt,
             retriever=st.session_state.vector_store.as_retriever(),
             llm=llm,
-            prompt=qa_prompt
+            combine_documents_chain=True
         )
 
         response = qa_chain({"question": query})