You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have a use case where I need to pass along metadata with each LLM request, since I use a proxy to log and report on all LLM usage. Similar to LiteLLM/Langfuse integration, as sample call would look like:
{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
"metadata": {
"trace_id": "trace-id22",
"trace_user_id": "user-id2"
}
```
Is there a way to capture the call and add the metadata before sending?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I have a use case where I need to pass along metadata with each LLM request, since I use a proxy to log and report on all LLM usage. Similar to LiteLLM/Langfuse integration, as sample call would look like:
Beta Was this translation helpful? Give feedback.
All reactions