代码初始化

inference/inference.py

@@ -27,7 +27,7 @@ async def fetch_model_response(payload: dict, headers: dict):
             raise HTTPException(status_code=response.status_code, detail=f"HTTP 错误: {e}")
 
 
-@router.post("/chat-completion/")
+@router.post("/chat-completion-academic/")
 async def chat_completion(token: str = Body(...), messages: list = Body(...)):
     try:
         # 创建 InferenceClient
@@ -53,6 +53,32 @@ async def chat_completion(token: str = Body(...), messages: list = Body(...)):
         raise HTTPException(status_code=500, detail=f"Error generating chat completion: {str(e)}")
 
 
+@router.post("/chat-completion/")
+async def chat_completion(token: str = Body(...), messages: list = Body(...)):
+    try:
+        # 创建 InferenceClient
+        client = InferenceClient(api_key=token)
+
+        messages.append({
+            "role": "system",
+            "content": "You are a multilingual chatbot capable of understanding questions in various languages and "
+                       "providing accurate responses in the appropriate language."
+        })
+
+        # 使用 chat API 请求生成模型的回答
+        completion = client.chat.completions.create(
+            model="google/gemma-2-2b-it",
+            messages=messages,
+            max_tokens=500
+        )
+
+        # 返回对话信息
+        return {"message": completion.choices[0].message}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error generating chat completion: {str(e)}")
+
+
 @router.post("/api-inference/")
 async def api_inference(
         authorization: str = Header(...),