Run the evaluation locally fails

[NanaXiong00]

Describe the issue:
When executing python ./src/evaluate.py --evaluation-name assistant-dev --evaluation-data-path ./src/data/ground_truth_sample.jsonl --metrics similarity according to README.md, the error is as follows:

Repro Steps:

1. Run git clone https://github.com/Azure-Samples/assistant-data-openai-python-promptflow
   and cd assistant-data-openai-python-promptflow
2. Run python -m venv .venv and .venv\scripts\activate
3. Run pip install -r ./src/requirements.txt
4. Run azd auth login
5. Run azd provision
6. Run azd deploy
7. Run pf flow test --flow ./src/copilot_sdk_flow/flow.flex.yaml --inputs chat_input="which month has peak sales in 2023"
8. Run python ./src/evaluate.py --evaluation-name assistant-dev --evaluation-data-path ./src/data/ground_truth_sample.jsonl --metrics similarity

Environment:

• Azd version: azd version 1.9.5 (commit cd2b7af9995d358aab33c782614f801ac1997dde)
• OS: Windows desktop

Expected behavior:
Run python ./src/evaluate.py --evaluation-name assistant-dev --evaluation-data-path ./src/data/ground_truth_sample.jsonl --metrics similarity can pass.

@jongio and @jfomhover for notification.