PR to update e2e tests for Ansible chatbot service including model evaluation n response.

[justjais]

Description

PR to update e2e tests for Ansible chatbot service including model evaluation n response. AAP-39070

Type of change

• Refactor
• New feature
• Bug fix
• CVE fix
• Optimization
• Documentation Update
• Configuration Update
• Bump-up dependent library
• Bump-up library or tool used for development (does not change the final image)
• CI configuration change
• Konflux configuration change

Related Tickets & Documents

• Related Issue #
• Closes #

Checklist before requesting a review

• I have performed a self-review of my code.
• PR has passed all pre-merge test jobs.
• If it is a core feature, I have added thorough tests.

Testing

• Run the eval test after copying the olsconfig file to parent directory
• Run the following cmd to test:

OPENAI_API_KEY=IGNORED python -m scripts.evaluation.driver --qna_pool_file ./ansible-chatbot-service/scripts/evaluation/eval_data/aap-sample.parquet --eval_provider_model_id my_rhoai_g3+granite3-8b --eval_metrics answer_relevancy answer_similarity_llm cos_score rougeL_precision --eval_modes ols --judge_model granite3-8b --judge_provider my_rhoai_g3 --eval_query_ids qna1 --eval_api_url https://stage.ai.ansible.redhat.com --eval_api_token_file ../stage_chatbot_token.txt

[justjais]

this is to accommodate GHA secret retrieval, as we cannot pass secret under a file WRT GHA

[TamiTakamiya]

@justjais Generally when we update files that are found in our upstream repo (road-core/service), we open a PR on the upstream repo first, then only deltas that are unique to AAP will be included in this repo.

Changes looked good and I will approve this PR, but would you consider porting some of those changes to road-core/service in the next sprint? Thanks.