llama-stack
llama-stack copied to clipboard
Improve CRUD on scoring function llm-as-judge
🚀 Describe the new functionality needed
We need to refactor llm-as-judge to make it easy for user to perform CRUD operations.
- unregister scoring functions
- persisting judge prompts
- migrating simpleqa judge prompts to other repo
https://github.com/meta-llama/llama-stack/pull/1405
💡 Why is this needed? What if we don't build it?
Prepare for llama-stack-evals repo
Other thoughts
No response