Update run.py

run.py

@@ -1,11 +1,35 @@
 import time
 import gradio as gr
+import requests
 
+# 使用 requests 库呼叫本地服務生成回應
+def generate_response(message, history):
+    url = "http://192.168.208.223:48763/v1/chat/completions"
+    headers = {"Content-Type": "application/json"}
+    data = {
+        "model": "deepseek-ai/deepseek-coder-6.7b-instruct",
+        "messages": [{"role": "user", "content": message}]
+    }
+    
+    response = requests.post(url, headers=headers, json=data)
+    
+    if response.status_code == 200:
+        return response.json()["choices"][0]["message"]["content"]
+    else:
+        return "抱歉，無法從模型獲得回應。"
+
+# 更新 slow_echo 函數，將其替換為使用 LLM 的邏輯
 def slow_echo(message, history):
+    # 模擬進度條效果，實際使用模型回應
     for i in range(len(message)):
-        time.sleep(0.05)
-        yield "You typed: " + message[: i + 1]
+        time.sleep(0.05)  # 模擬延遲
+        yield "你輸入了: " + message[: i + 1]
+    
+    # 呼叫 LLM 生成回應
+    llm_response = generate_response(message, history)
+    yield llm_response
 
+# 設置 Gradio 的聊天界面
 demo = gr.ChatInterface(
     slow_echo,
     type="messages",