Merge pull request #2752 from BerriAI/litellm_grafana_metrics

[Fix + Docs] grafana / prometheus metrics

docs/my-website/docs/proxy/grafana_metrics.md

@@ -4,6 +4,8 @@ LiteLLM Exposes a `/metrics` endpoint for Prometheus to Poll
 
 ## Quick Start
 
+If you're using the LiteLLM CLI with `litellm --config proxy_config.yaml` then you need to `pip install prometheus_client==0.20.0`. **This is already pre-installed on the litellm Docker image**
+
 Add this to your proxy config.yaml 
 ```yaml
 model_list:
@@ -34,6 +36,12 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 }'
 ```
 
+View Metrics on `/metrics`, Visit `http://localhost:4000/metrics` 
+```shell
+http://localhost:4000/metrics
+
+# <proxy_base_url>/metrics
+```
 
 ## Metrics Tracked 
 

litellm/proxy/proxy_config.yaml

@@ -43,8 +43,5 @@ model_list:
       model: openai/fake
       api_key: fake-key
       api_base: https://exampleopenaiendpoint-production.up.railway.app/
-general_settings:
-  master_key: sk-1234
-  disable_spend_logs: true
-  disable_reset_budget: true
-  num_retries: 2
+litellm_settings:
+  success_callback: ["prometheus"]

litellm/utils.py

@@ -6235,7 +6235,8 @@ def set_callbacks(callback_list, function_id=None):
             elif callback == "datadog":
                 dataDogLogger = DataDogLogger()
             elif callback == "prometheus":
-                prometheusLogger = PrometheusLogger()
+                if prometheusLogger is None:
+                    prometheusLogger = PrometheusLogger()
             elif callback == "dynamodb":
                 dynamoLogger = DyanmoDBLogger()
             elif callback == "s3":