docs update

docs/my-website/docs/observability/callbacks.md

@@ -6,6 +6,7 @@ liteLLM provides `success_callbacks` and `failure_callbacks`, making it easy for
 
 liteLLM supports:
 
+- [Custom Callback Functions](https://docs.litellm.ai/docs/observability/custom_callback)
 - [LLMonitor](https://llmonitor.com/docs)
 - [Helicone](https://docs.helicone.ai/introduction)
 - [Traceloop](https://traceloop.com/docs)

docs/my-website/docs/observability/custom_callback.md

@@ -10,6 +10,11 @@ def custom_callback(
     start_time, end_time    # start/end time
 ):
     # Your custom code here
+    print("LITELLM: in custom callback function")
+    print("kwargs", kwargs)
+    print("completion_response", completion_response)
+    print("start_time", start_time)
+    print("end_time", end_time)
 ```
 
 ## Using Your Custom Callback Function
@@ -35,6 +40,39 @@ print(response)
 
 ```
 
+### Custom Callback to write to Mixpanel
+
+```python
+import mixpanel
+import litellm
+from litellm import completion
+
+def custom_callback(
+    kwargs,                 # kwargs to completion
+    completion_response,    # response from completion
+    start_time, end_time    # start/end time
+):
+    # Your custom code here
+    mixpanel.track("LLM Response", {"llm_response": completion_response})
+
+
+# Assign the custom callback function
+litellm.success_callback = [custom_callback]
+
+response = completion(
+    model="gpt-3.5-turbo",
+    messages=[
+        {
+            "role": "user",
+            "content": "Hi 👋 - i'm openai"
+        }
+    ]
+)
+
+print(response)
+
+```
+