Retrieval quality directly impacts the quality of output from your AI application. While testing prompts, Maxim allows you to connect your RAG pipeline via a simple API endpoint and evaluates the retrieved context for every run. Context specific evaluators for precision, recall and relevance make it easy to see where retrieval quality is low.
Create a Context Source
Configure your RAG endpoint
Add context variable to your prompt
{{context}}
in your prompt to provide instructions on using this dynamic data.Link the Context Source
Test with real-time retrieval
Initiate prompt testing
Select your test dataset
Choose context evaluation source
context to evaluate
, select the dynamic Context SourceAdd retrieval quality evaluators
Review retrieved context results
Examine detailed chunk information
Analyze evaluator feedback
evaluation
tab. Use this to debug retrieval issues.