Update app.py

app.py

@@ -32,11 +32,12 @@ else:
 
 def respond(
     message,
-    #history: list[tuple[str, str]],
-    #system_message,
+    history: list[tuple[str, str]],
+    system_message,
     max_tokens,
-    temperature,
-    top_p):
+    temperature
+    #top_p
+    ):
 
     # define retriever object
     retriever = vectordb.as_retriever(search_type="similarity", search_kwargs={"k": 5})
@@ -50,15 +51,17 @@ def respond(
     # create a RAG pipeline
     qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
     #generate results
-    result = qa_chain.invoke(query)
+    result = qa_chain.invoke(message)
     
     yield result['result']
 
 
 demo = gr.ChatInterface(
     respond,
+    type="messages", 
+    autofocus=False,
     additional_inputs=[
-        #gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=128, maximum=1024, value=512, step=128, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -66,7 +69,7 @@ demo = gr.ChatInterface(
             maximum=1.0,
             value=0.95,
             step=0.05,
-            #label="Top-p (nucleus sampling)",
+            label="Top-p (nucleus sampling)",
         ),
     ],
 )