代码初始化

inference/inference.py

@@ -58,7 +58,7 @@ async def chat_completion(token: str = Body(...), messages: list = Body(...)):
     try:
         # 创建 InferenceClient
         client = InferenceClient(api_key=token)
-
+        print("问题：", messages)
         messages.append({
             "role": "system",
             "content": "You are a multilingual chatbot capable of understanding questions in various languages and "
@@ -66,9 +66,9 @@ async def chat_completion(token: str = Body(...), messages: list = Body(...)):
                        "answered in Chinese."
         })
 
-        # 使用 chat API 请求生成模型的回答
+        # 使用 chat API 请求生成模型的回答  备选模型  google/gemma-2-2b-it
         completion = client.chat.completions.create(
-            model="google/gemma-2-2b-it",
+            model="mistralai/Mistral-Nemo-Instruct-2407",
             messages=messages,
             max_tokens=500
         )