Langfuse vs Helicone
The helicone integration seems to be a lot simpler and lightweight but I'm wondering if there's any downsides I'm not aware of?
Solution:Jump to solution
Proxy implementations make it very simple to trace llm calls whereas Langfuse traces asynchronously on the application level.
Upside proxy: change basepath and done
Upside application-level:...
Observability for LiteLLM - Langfuse
Open source observability for LiteLLM via the native integration. Automatically capture detailed traces and metrics for every request.
1 Reply
Solution
Proxy implementations make it very simple to trace llm calls whereas Langfuse traces asynchronously on the application level.
Upside proxy: change basepath and done
Upside application-level:
- trace non-llm calls and frameworks - eg retrieved documents in RAG or API calls
- no uptime impact
- no latency impact
If you prefer the proxy approach and don’t need tracing of non-llm pieces of your application, you can use LiteLLM + Langfuse which makes this super simple. Have a look here: https://langfuse.com/docs/integrations/litellm/tracing
Observability for LiteLLM - Langfuse
Open source observability for LiteLLM via the native integration. Automatically capture detailed traces and metrics for every request.