From acd8facf9899014a76d5cb053176bb3e33cb0162 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Thu, 26 Sep 2024 10:22:14 -0700
Subject: [PATCH] fix(litellm_logging.py): don't initialize prometheus_logger
 if non premium user

Prevents bad error messages in logs

Fixes https://github.com/BerriAI/litellm/issues/5897
---
 litellm/litellm_core_utils/litellm_logging.py | 22 +++++++++++++------
 ...odel_prices_and_context_window_backup.json | 11 ++++++++++
 litellm/proxy/utils.py                        |  5 +++++
 litellm/utils.py                              |  4 ++--
 4 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index 1219feac9e6..23761048bf3 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -31,6 +31,7 @@ from litellm.litellm_core_utils.redact_messages import (
     redact_message_input_output_from_custom_logger,
     redact_message_input_output_from_logging,
 )
+from litellm.proxy._types import CommonProxyErrors
 from litellm.rerank_api.types import RerankResponse
 from litellm.types.llms.openai import HttpxBinaryResponseContent
 from litellm.types.router import SPECIAL_MODEL_INFO_PARAMS
@@ -2140,7 +2141,8 @@ def _init_custom_logger_compatible_class(
     llm_router: Optional[
         Any
     ],  # expect litellm.Router, but typing errors due to circular import
-) -> CustomLogger:
+    premium_user: bool = False,
+) -> Optional[CustomLogger]:
     if logging_integration == "lago":
         for callback in _in_memory_loggers:
             if isinstance(callback, LagoLogger):
@@ -2174,13 +2176,19 @@ def _init_custom_logger_compatible_class(
         _in_memory_loggers.append(_langsmith_logger)
         return _langsmith_logger  # type: ignore
     elif logging_integration == "prometheus":
-        for callback in _in_memory_loggers:
-            if isinstance(callback, PrometheusLogger):
-                return callback  # type: ignore
+        if premium_user:
+            for callback in _in_memory_loggers:
+                if isinstance(callback, PrometheusLogger):
+                    return callback  # type: ignore
 
-        _prometheus_logger = PrometheusLogger()
-        _in_memory_loggers.append(_prometheus_logger)
-        return _prometheus_logger  # type: ignore
+            _prometheus_logger = PrometheusLogger()
+            _in_memory_loggers.append(_prometheus_logger)
+            return _prometheus_logger  # type: ignore
+        else:
+            verbose_logger.warning(
+                f"🚨🚨🚨 Prometheus Metrics is on LiteLLM Enterprise\n🚨 {CommonProxyErrors.not_premium_user.value}"
+            )
+            return None
     elif logging_integration == "datadog":
         for callback in _in_memory_loggers:
             if isinstance(callback, DataDogLogger):
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 0cd996289fa..e801788ad35 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2434,6 +2434,17 @@
         "mode": "chat",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models"
     },
+    "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": {
+        "max_tokens": 8192,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.0,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai-llama_models",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas"
+    },
     "vertex_ai/mistral-large@latest": {
         "max_tokens": 8191,
         "max_input_tokens": 128000,
diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py
index 80eea79fbc7..4dbacc0f4e3 100644
--- a/litellm/proxy/utils.py
+++ b/litellm/proxy/utils.py
@@ -296,6 +296,7 @@ class ProxyLogging:
     def __init__(
         self,
         user_api_key_cache: DualCache,
+        premium_user: bool = False,
     ):
         ## INITIALIZE  LITELLM CALLBACKS ##
         self.call_details: dict = {}
@@ -318,6 +319,7 @@ class ProxyLogging:
             alert_types=self.alert_types,
             internal_usage_cache=self.internal_usage_cache.dual_cache,
         )
+        self.premium_user = premium_user
 
     def update_values(
         self,
@@ -378,7 +380,10 @@ class ProxyLogging:
                     callback,
                     internal_usage_cache=self.internal_usage_cache.dual_cache,
                     llm_router=llm_router,
+                    premium_user=self.premium_user,
                 )
+                if callback is None:
+                    continue
             if callback not in litellm.input_callback:
                 litellm.input_callback.append(callback)  # type: ignore
             if callback not in litellm.success_callback:
diff --git a/litellm/utils.py b/litellm/utils.py
index 1c9d7bde7cd..a63c25393ac 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -367,7 +367,7 @@ def function_setup(
                     callback = litellm.litellm_core_utils.litellm_logging._init_custom_logger_compatible_class(  # type: ignore
                         callback, internal_usage_cache=None, llm_router=None
                     )
-                    if any(
+                    if callback is None or any(
                         isinstance(cb, type(callback))
                         for cb in litellm._async_success_callback
                     ):  # don't double add a callback
@@ -431,7 +431,7 @@ def function_setup(
                     )
 
                     # don't double add a callback
-                    if not any(
+                    if callback_class is not None and not any(
                         isinstance(cb, type(callback_class)) for cb in litellm.callbacks
                     ):
                         litellm.callbacks.append(callback_class)  # type: ignore