Your previous status:
textarea-Umapathy |
|---|
Today, I created a new dataset as the golden copy for our use cases, and I am now evaluating the scores for these use cases(New System Prompt & Old System Prompt) in the Langfuse tool. Also, I have implemented the additional layer to measure our RAG performance. Also please see the below files and results now. Also, currently working with the score category(Low,..Excellent) wise also |