Update app.py

app.py

@@ -62,17 +62,37 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         styled_thought = f'<div class="markdown-think">{reasoning.strip()}</div>'
         yield styled_thought
 
+    time.sleep(0.5)
+
+    final_prompt = messages + [
+        {"role": "user", "content": message},
+        {"role": "assistant", "content": reasoning.strip()},
+        {"role": "user", "content": "Now answer based on your reasoning above."}
+    ]
+
+    final_answer = ""
+    for chunk in client.chat_completion(
+        final_prompt,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = chunk.choices[0].delta.content or ""
+        final_answer += token
+        yield final_answer.strip()
+
 demo = gr.ChatInterface(
     fn=respond,
-    title="λmabdAI",
+    title="λambdAI",
     theme=gr.themes.Base(),
     css=css,
     additional_inputs=[
         gr.Textbox(value="You are a concise, logical AI that explains its reasoning clearly before answering.",
-                   label="System Message", elem_classes=["jetbrains"]),
-        gr.Slider(64, 2048, value=512, step=1, label="Max Tokens", elem_classes=["jetbrains"]),
-        gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature", elem_classes=["jetbrains"]),
-        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p", elem_classes=["jetbrains"])
+                   label="System Message"),
+        gr.Slider(64, 2048, value=512, step=1, label="Max Tokens"),
+        gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
     ]
 )