fix rag_workflow run in each trial

[r0ymanesco]

Move the evaluation_dataset creation to _outer_objective in order to reinitialise on each objective computation

[github-actions[bot]]

Coverage report

Click to see where and how coverage changed

File	Statements	Missing	Coverage	Coverage (new stmts)	Lines missing
notdiamond/llms
client.py
notdiamond/toolkit
langchain.py
notdiamond/toolkit/litellm
main.py
notdiamond/toolkit/rag
workflow.py
tests/test_components/test_llms
test_llm.py
tests/test_toolkit/langchain
test_unit.py
tests/test_toolkit/rag
test_example_workflow.py
test_workflow.py
Project Total

This report was generated by python-coverage-comment-action