Update app.py

app.py

@@ -103,46 +103,17 @@ def load_llm(api_key):
         model_kwargs={"temperature": 0.5, "max_length": 100}
     )
 
-# def ask_question(question, retriever, llm):
-#     """Uses a QA chain to retrieve and answer a question."""
-#     qa_chain = RetrievalQA.from_chain_type(
-#         retriever=retriever,
-#         chain_type="stuff",
-#         llm=llm,
-#         return_source_documents=False
-#     )
-#     response = qa_chain.invoke({"query": question})
-#     return response["result"]
-
-from langchain.prompts import PromptTemplate
-
 def ask_question(question, retriever, llm):
     """Uses a QA chain to retrieve and answer a question."""
-    # Define the custom prompt template
-    prompt_template = PromptTemplate(
-        input_variables=["context", "query"],
-        template="You are an assistant. Answer the user's question based on the context below. "
-                 "Do not reference the dataset or provide unnecessary details.\n\n"
-                 "Context: {context}\n\n"
-                 "Question: {query}\n\n"
-                 "Answer:"
-    )
-
-    # Create the QA chain
     qa_chain = RetrievalQA.from_chain_type(
         retriever=retriever,
         chain_type="stuff",
         llm=llm,
-        return_source_documents=False,
-        chain_type_kwargs={"prompt": prompt_template}
+        return_source_documents=False
     )
-
-    # Pass the question in a dictionary to match the required input keys
     response = qa_chain.invoke({"query": question})
     return response["result"]
-
-
-
+    
 # Streamlit App
 def upload_data():
     st.title("Upload Dataset")