Skip to content

chore: add CI configuration files and environment variable substitution script#39

Open
dumians wants to merge 1 commit intomainfrom
CI_Onboarding
Open

chore: add CI configuration files and environment variable substitution script#39
dumians wants to merge 1 commit intomainfrom
CI_Onboarding

Conversation

@dumians
Copy link
Copy Markdown
Contributor

@dumians dumians commented May 5, 2026

feat: This PR introduces an automated Evalbench CI pipeline for evaluating the Oracle DB extension .

Key Changes:
Cloud Build Pipeline: Adds cloudbuild.yaml to orchestrate the Evalbench standalone evaluation.
Evaluation Configs: Adds configurations (dataset.json, run_config.yaml, model_config.yaml) to define and test core scenarios like debugging instances and checking performance.
Trigger Label: Introduces the ci:run-evals GitHub label to manually trigger the evaluation pipeline on pull requests.

@dumians dumians requested review from a team as code owners May 5, 2026 06:47
@github-actions github-actions Bot requested a review from Matthieu68857 May 5, 2026 06:47
Comment thread evals/dataset.json
{
"id": "oracledb-query-execution",
"starting_prompt": "I want to run a query to get insights from my database.",
"conversation_plan": "First, ask the agent to execute a simple SELECT query (e.g., SELECT * FROM users LIMIT 5) to verify connectivity and permissions. After the agent provides the results, ask it to execute a more complex query that involves a JOIN between two tables (e.g., SELECT orders.id, users.name FROM orders JOIN users ON orders.user_id = users.id LIMIT 5).",
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are you planning to add failure scenarios as well?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants