Open dcecchini opened 12 months ago
We should add tests and benchmarks for RAG evaluation.
We can start with the ragas evaluation metric:
ragas
Implement in library but give reference.
Evaluate LLMs and RAG a practical example using Langchain and Hugging Face
https://www.philschmid.de/evaluate-llm?ref=blog.langchain.dev
We should add tests and benchmarks for RAG evaluation.
We can start with the
ragas
evaluation metric: