Update app.py

app.py

@@ -8,42 +8,27 @@ client = InferenceClient(model)
 
 def fn(
     prompt,
-    #history: list[tuple[str, str]],
     history,
-    #system_prompt,
+    system_prompt,
     max_tokens,
     temperature,
     top_p,
 ):
-    #messages = [{"role": "system", "content": system_prompt}]
-    #history.append({"role": "user", "content": prompt})
+    messages = [{"role": "system", "content": system_prompt}]
+    messages.append({"role": "user", "content": prompt})
     
-    messages = [{"role": "user", "content": prompt}]
+    #messages = [{"role": "user", "content": prompt}]
     
     history.append(messages[0])
 
-    #for val in history:
-    #    if val[0]:
-    #        messages.append({"role": "user", "content": val[0]})
-    #    if val[1]:
-    #        messages.append({"role": "assistant", "content": val[1]})
-    
-    #messages.append({"role": "user", "content": prompt})
-
     stream = client.chat.completions.create(
         model = model,
-        #messages = messages,
         messages = history,
         max_tokens = max_tokens,
         temperature = temperature,
         top_p = top_p,
         stream = True
     )
-    
-    #response = ""
-    #for chunk in stream:
-    #    response += chunk.choices[0].delta.content
-    #return response
 
     chunks = []
     for chunk in stream:
@@ -54,7 +39,7 @@ app = gr.ChatInterface(
     fn = fn,
     type = "messages",
     additional_inputs = [
-        #gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
+        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-P"),