add banbanmini backend

talkingq-url/interfaces/llm.py

@@ -0,0 +1,19 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, AsyncGenerator
+
+
+class LLM(ABC):
+    @abstractmethod
+    async def generate_response_stream(
+        self, transcript: str, history: List[Dict[str, str]], selected_role: dict
+    ) -> AsyncGenerator[str, None]:
+        
+        pass
+
+    async def close(self):
+        
+        pass
+
+    async def connect(self):
+        
+        pass