Update app.py

app.py

@@ -94,14 +94,13 @@ def generate_response(query, history, model, temperature, max_tokens, top_p, see
     custom_rag_prompt = PromptTemplate.from_template(template)
 
     
-    # Step 1: Prepare inputs manually
-    docs = retriever.invoke(query)
-    context = format_docs(docs)
-    inputs = {"context": context, "question": query}
-
-    # Step 2: Get the final prompt string
-    prompt_value = custom_rag_prompt.invoke(inputs)
-    final_prompt = prompt_value.to_string()
+    # Retrive the final prompt that sent to the LLM
+    docs = retriever.invoke(query)
+    context = format_docs(docs)
+    inputs = {"context": context, "question": query}
+
+    prompt_value = custom_rag_prompt.invoke(inputs)
+    final_prompt = prompt_value.to_string()
     print("Final Prompt Sent to LLM:\n", final_prompt)
 
     rag_chain = (