I have an LLM built on AZUREOPENAI. I have a set of questions and answers which I have to use as a input and expected_output. I don't have actual_output, context, retriveal_context. I have been through the Deepeval documentation, tried a few options, but got confused with it. I can connect to my LLM as per the deepeval documentation. Can you help me in guiding how can I start building test cases or start evaluating inputs/outputs with deepeval? referred links: https://www.hanaloop.com/docs/x40_engineering/2024-10-22-evaluation-with-deepeval/ https://www.deepeval.com/guides/guides-using-custom-llms https://medium.com/@rajveer.rathod1...-a-comprehensive-practical-guide-e55ef1f9eeab Continue reading...
