优化dockerfile，增加docker-compose，async openai

Dockerfile

@@ -3,16 +3,18 @@ FROM python:3.10-slim
 WORKDIR /app
 
 # 复制所需文件到容器中
-COPY ./app /app/app
 COPY ./requirements.txt /app
 
 RUN pip install --no-cache-dir -r requirements.txt
+COPY ./app /app/app
 ENV API_KEYS='["your_api_key_1"]'
 ENV ALLOWED_TOKENS='["your_token_1"]'
 ENV BASE_URL=https://generativelanguage.googleapis.com/v1beta
 ENV TOOLS_CODE_EXECUTION_ENABLED=true
 ENV MODEL_SEARCH='["gemini-2.0-flash-exp"]'
 
+COPY ./api_keys.txt /app
+
 # Expose port
 EXPOSE 8000
 

app/services/openai_chat_service.py

@@ -137,13 +137,13 @@ class OpenAIChatService:
 
         if request.stream:
             return self._handle_stream_completion(request.model, payload, api_key)
-        return self._handle_normal_completion(request.model, payload, api_key)
+        return await self._handle_normal_completion(request.model, payload, api_key)
 
-    def _handle_normal_completion(
+    async def _handle_normal_completion(
             self, model: str, payload: Dict[str, Any], api_key: str
     ) -> Dict[str, Any]:
         """处理普通聊天完成"""
-        response = self.api_client.generate_content(payload, model, api_key)
+        response = await self.api_client.generate_content(payload, model, api_key)
         return self.response_handler.handle_response(
             response, model, stream=False, finish_reason="stop"
         )

docker-compose.yml

@@ -0,0 +1,9 @@
+version: '3'
+
+services:
+  gemini-balance:
+    build: .
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env