Update app.py

app.py

@@ -18,16 +18,16 @@ def save_database(database):
     with open(DATABASE_PATH, "w") as file:
         json.dump(database, file)
 
-def format_prompt(message, history):
+def format_prompt(message, system, history):
     # Format prompt according to the new template
-    prompt = "SYSTEM: You are a helpful assistant, with no access to external functions.\n<|endofsystem|>\n"
+    prompt = f"SYSTEM: {system}\n<|endofsystem|>\n"
     for user_prompt, bot_response in history:
         prompt += f"USER: {user_prompt}\n\n\nASSISTANT: {bot_response}<|endoftext|>\n"
     prompt += f"USER: {message}\n\n\nASSISTANT:"
     return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_new_tokens=4096, top_p=0.9, repetition_penalty=1.2,
+    prompt, system, history, temperature=0.9, max_new_tokens=4096, top_p=0.9, repetition_penalty=1.2,
 ):
     database = load_database()  # Load the database
     temperature = float(temperature)
@@ -47,17 +47,62 @@ def generate(
 
     yield response_text
 
-css = """
-  #mkd {
-    height: 500px; 
-    overflow: auto; 
-    border: 1px solid #ccc; 
-  }
+customCSS = """
+#component-7 { # this is the default element ID of the chat component
+  height: 1600px; # adjust the height as needed
+  flex-grow: 4;
+}
 """
 
-with gr.Blocks(css=css) as demo:
+additional_inputs=[
+    gr.TextBox(
+        label="System prompt",
+        value="You are a helpful assistant, with no access to external functions.",
+        info="System prompt",
+        interactive=True,
+    ),
+    gr.Slider(
+        label="Temperature",
+        value=0.9,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=1024,
+        minimum=64,
+        maximum=4096,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+    gr.Slider(
+        label="Top-p (nucleus sampling)",
+        value=0.90,
+        minimum=0.0,
+        maximum=1,
+        step=0.05,
+        interactive=True,
+        info="Higher values sample more low-probability tokens",
+    ),
+    gr.Slider(
+        label="Repetition penalty",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Penalize repeated tokens",
+    )
+]
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.ChatInterface(
         generate,
+        additional_inputs=additional_inputs,
     )
 
-demo.launch(debug=True)
+demo.queue().launch(debug=True)