Next Steps
β Add Ranker to your pipeline to increase the context relevance
β Use local models to evaluate your pipeline
β Change the splitting strategy
β Generate ground-truth documents for retrieval evaluation π‘
β Check out the Evaluation Walkthrough
β Use a tracing tool for continuous evaluation: Langfuse, Arize
Slide 10
Slide 10 text
@bilgeycl
in/bilgeyucel
Q&A
Cookbook: Evaluating AI with Haystack