Feature: Router aembedding

litellm/router.py

@@ -112,7 +112,20 @@ class Router:
         data["caching"] = self.cache_responses
         # call via litellm.embedding() 
         return litellm.embedding(**{**data, **kwargs})
-    
+
+    async def aembedding(self,
+                         model: str,
+                         input: Union[str, List],
+                         is_async: Optional[bool] = True,
+                         **kwargs) -> Union[List[float], None]:
+        # pick the one that is available (lowest TPM/RPM)
+        deployment = self.get_available_deployment(model=model, input=input)
+
+        data = deployment["litellm_params"]
+        data["input"] = input
+        data["caching"] = self.cache_responses
+        return await litellm.aembedding(**{**data, **kwargs})
+
     def set_model_list(self, model_list: list):
         self.model_list = model_list
 

litellm/tests/test_router.py

@@ -181,3 +181,29 @@ def test_acompletion_on_router():
 	except Exception as e:
 		traceback.print_exc()
 		pytest.fail(f"Error occurred: {e}")
+
+
+def test_aembedding_on_router():
+	try:
+		model_list = [
+			{
+				"model_name": "text-embedding-ada-002",
+				"litellm_params": {
+					"model": "text-embedding-ada-002",
+				},
+				"tpm": 100000,
+				"rpm": 10000,
+			},
+		]
+
+		async def embedding_call():
+			router = Router(model_list=model_list)
+			response = await router.aembedding(
+				model="text-embedding-ada-002",
+				input=["good morning from litellm", "this is another item"],
+			)
+			print(response)
+		asyncio.run(embedding_call())
+	except Exception as e:
+		traceback.print_exc()
+		pytest.fail(f"Error occurred: {e}")