Merge pull request #5463 from BerriAI/litellm_track_error_per_model

[Feat - Prometheus] - Track error_code, model metric

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

@@ -58,6 +58,15 @@ http://localhost:4000/metrics
 
 ## 📈 Metrics Tracked 
 
+### Error Metrics
+
+| Metric Name          | Description                          |
+|----------------------|--------------------------------------|
+| `litellm_error_code_metric_total`             | Total number of errors by error code and model |
+
+This metric provides a count of errors encountered, categorized by error code and model. For example:
+
+
 
 ### Proxy Requests / Spend Metrics
 
@@ -66,7 +75,12 @@ http://localhost:4000/metrics
 | `litellm_requests_metric`             | Number of requests made, per `"user", "key", "model", "team", "end-user"`          |
 | `litellm_spend_metric`                | Total Spend, per `"user", "key", "model", "team", "end-user"`                 |
 | `litellm_total_tokens`         | input + output tokens per `"user", "key", "model", "team", "end-user"`     |
+
+### Error Monitoring Metrics
+
+| Metric Name          | Description                          |
 | `litellm_llm_api_failed_requests_metric`   | Number of failed LLM API requests per `"user", "key", "model", "team", "end-user"`    |
+| `litellm_error_code_metric_total`             | Total number of errors by error code and model |
 
 ### Request Latency Metrics 
 

litellm/integrations/prometheus.py

@@ -138,6 +138,13 @@ class PrometheusLogger(CustomLogger):
                 labelnames=["hashed_api_key", "api_key_alias", "model"],
             )
 
+            # New metric for tracking error codes and models
+            self.litellm_error_code_metric = Counter(
+                "litellm_error_code_metric",
+                "Total number of errors by error code and model",
+                labelnames=["error_code", "model"],
+            )
+
             # Litellm-Enterprise Metrics
             if premium_user is True:
 
@@ -378,7 +385,7 @@ class PrometheusLogger(CustomLogger):
         from litellm.proxy.proxy_server import premium_user
 
         verbose_logger.debug(
-            f"prometheus Logging - Enters success logging function for kwargs {kwargs}"
+            f"prometheus Logging - Enters failure logging function for kwargs {kwargs}"
         )
 
         # unpack kwargs
@@ -409,6 +416,16 @@ class PrometheusLogger(CustomLogger):
                 user_id,
             ).inc()
             self.set_llm_deployment_failure_metrics(kwargs)
+
+            _exception = kwargs.get("exception", None)
+            error_code = "unknown"
+            if _exception is not None and hasattr(_exception, "status_code"):
+                error_code = _exception.status_code
+
+            # Increment the new error code metric
+            self.litellm_error_code_metric.labels(
+                error_code=error_code, model=model
+            ).inc()
         except Exception as e:
             verbose_logger.exception(
                 "prometheus Layer Error(): Exception occured - {}".format(str(e))

litellm/proxy/proxy_config.yaml

@@ -3,21 +3,12 @@ model_list:
    litellm_params:
      model: openai/fake
      api_key: fake-key
-     api_base: https://exampleopenaiendpoint-production.up.railway.app/
-     tags: ["teamA"] # 👈 Key Change
    model_info:
      id: "team-a-model" # used for identifying model in response headers
- - model_name: fake-openai-endpoint
-   litellm_params:
-     model: openai/fake
-     api_key: fake-key
-     api_base: https://exampleopenaiendpoint-production.up.railway.app/
-     tags: ["teamB"] # 👈 Key Change
-   model_info:
-     id: "team-b-model" # used for identifying model in response headers
 
-router_settings:
+litellm_settings:
- enable_tag_filtering: True # 👈 Key Change
+  success_callback: ["prometheus"]
+  failure_callback: ["prometheus"]
 
 general_settings: 
  master_key: sk-1234