Merge branch 'main' into litellm_redis_team_object

litellm/proxy/_new_secret_config.yaml

@@ -1,9 +1,11 @@
 model_list:
-  - model_name: "*"             # all requests where model not in your config go to this deployment
+  - model_name: "test-model"             
     litellm_params:
-      model: "openai/*"           # passes our validation check that a real provider is given
-      api_key: "" 
+      model: "openai/text-embedding-ada-002"
+  - model_name: "my-custom-model"
+    litellm_params:
+      model: "my-custom-llm/my-model"
 
 litellm_settings:
-  cache: True
-  
+  custom_provider_map:
+  - {"provider": "my-custom-llm", "custom_handler": custom_handler.my_custom_llm}

litellm/proxy/custom_handler.py

@@ -0,0 +1,21 @@
+import litellm
+from litellm import CustomLLM, completion, get_llm_provider
+
+
+class MyCustomLLM(CustomLLM):
+    def completion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+    async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
+        return litellm.completion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "Hello world"}],
+            mock_response="Hi!",
+        )  # type: ignore
+
+
+my_custom_llm = MyCustomLLM()

litellm/proxy/management_endpoints/internal_user_endpoints.py

@@ -27,6 +27,7 @@ from litellm._logging import verbose_proxy_logger
 from litellm.proxy._types import *
 from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
 from litellm.proxy.management_endpoints.key_management_endpoints import (
+    _duration_in_seconds,
     generate_key_helper_fn,
 )
 from litellm.proxy.management_helpers.utils import (
@@ -486,6 +487,13 @@ async def user_update(
             ):  # models default to [], spend defaults to 0, we should not reset these values
                 non_default_values[k] = v
 
+        if "budget_duration" in non_default_values:
+            duration_s = _duration_in_seconds(
+                duration=non_default_values["budget_duration"]
+            )
+            user_reset_at = datetime.now(timezone.utc) + timedelta(seconds=duration_s)
+            non_default_values["budget_reset_at"] = user_reset_at
+
         ## ADD USER, IF NEW ##
         verbose_proxy_logger.debug("/user/update: Received data = %s", data)
         if data.user_id is not None and len(data.user_id) > 0:

litellm/proxy/proxy_config.yaml

@@ -8,6 +8,12 @@ model_list:
     litellm_params:
       model: fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct
       api_key: "os.environ/FIREWORKS"
+  - model_name: tts
+    litellm_params:
+      model: openai/tts-1
+      api_key: "os.environ/OPENAI_API_KEY"
+    model_info:
+      mode: audio_speech
 general_settings: 
   master_key: sk-1234
   alerting: ["slack"]

litellm/proxy/proxy_server.py

@@ -1507,6 +1507,21 @@ class ProxyConfig:
                     verbose_proxy_logger.debug(
                         f"litellm.post_call_rules: {litellm.post_call_rules}"
                     )
+                elif key == "custom_provider_map":
+                    from litellm.utils import custom_llm_setup
+
+                    litellm.custom_provider_map = [
+                        {
+                            "provider": item["provider"],
+                            "custom_handler": get_instance_fn(
+                                value=item["custom_handler"],
+                                config_file_path=config_file_path,
+                            ),
+                        }
+                        for item in value
+                    ]
+
+                    custom_llm_setup()
                 elif key == "success_callback":
                     litellm.success_callback = []
 
@@ -3334,6 +3349,7 @@ async def embeddings(
         if (
             "input" in data
             and isinstance(data["input"], list)
+            and len(data["input"]) > 0
             and isinstance(data["input"][0], list)
             and isinstance(data["input"][0][0], int)
         ):  # check if array of tokens passed in
@@ -3464,8 +3480,8 @@ async def embeddings(
             litellm_debug_info,
         )
         verbose_proxy_logger.error(
-            "litellm.proxy.proxy_server.embeddings(): Exception occured - {}".format(
-                str(e)
+            "litellm.proxy.proxy_server.embeddings(): Exception occured - {}\n{}".format(
+                str(e), traceback.format_exc()
             )
         )
         verbose_proxy_logger.debug(traceback.format_exc())