Open saiprasath21 opened 3 weeks ago
he @saiprasath21 you can do that with Explainability through Logging and tracing - Ragas or writting your own langchain callbacks
but can you check out the docs and let me know if it works for you 🙂
Hey @jjmachan , yes this helps a lot.
I'm now passing a langfuse call handler to ragas using the evaluate func. However, all my dataset item spans are recorded under the same trace. Is there a way to create a separate trace for each dataset item?
[ ] I checked the documentation and related resources and couldn't find an answer to my question.
I want to get all the intermediate steps performed while getting a metric score. This will be helpful to understand why the model took a particular action.