any chance you can link me to one? preferably RAG?
Are there any code examples on how I can integrate Phoenix tracer with custom RAG agent (an agent that does not use popular frameworks like LlamaIndex?
Does Pheonix support bringing my own LLMs for task evaluation? Will I still be able to use out of the box evals with a BYO backend LLM?
I鈥檓 considering phoenix for some proof of concept work for ML observability.
How does it compare to Evidently and other open source ML Observability solutions?
How does the LLM eval in Phoenix compare to Guardrails AI evals?
