Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request

Medium

Please provide a clear description of problem this feature solves

Currently workflow has observability support but evaluation doesn't. Evaluation can also get expensive in terms of LLM usage (depending on the evaluator) and there is value in being able to trace the LLM usage. When using W&B weave you can see all LLM traces (because of the additional monkey-patching done by weave) but the evaluation traces show up with no context (standalone chains) and that can be confusing for the user.

Describe your ideal solution

Each evaluate function should create its own chain

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct
• I have searched the open feature requests and have found no duplicates for this feature request