Skip to content

Change Config to upload conversation history to BigQuery #457

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
graceqi-g merged 3 commits into from
Jun 24, 2026
+10 −1
Merged

Change Config to upload conversation history to BigQuery #457

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8e27e75
fix(dea): accumulate all agent text parts and increase timeout
Jun 23, 2026
9f12284
docs(dea): configure BigQuery reporting and document results inspection
Jun 23, 2026
3f008d1
Merge branch 'main' into upload_conversation_history
IsmailMehdi Jun 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion datasets/dea-tools/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,13 @@ EVAL_DEA_WORKSPACE_ID=<YOUR_WORKSPACE_ID> \
* `EVAL_DEA_WORKSPACE_ID`: The target Dataform workspace ID (short name).

## 4. Inspect Results
Upon completion, results will be generated under the `results/` folder:
Upon completion, results will be generated in two locations:

### Local Files (under the `results/` folder):
* `evals.csv`: Contains the full conversation history.
* `scores.csv`: Contains LLM-Judge scores and detailed reasoning for the rubric checks.

### Google BigQuery (Cloud Database):
If enabled in `example_run_config.yaml`, results are automatically uploaded to your GCP project under the table `<YOUR_GCP_PROJECT_ID>.evalbench.results`.

A clickable **Looker Studio Dashboard** link will be printed in the terminal console upon completion to visually inspect the conversation flows and scores.
2 changes: 2 additions & 0 deletions datasets/dea-tools/example_run_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,5 +21,7 @@ scorers:
reporting:
csv:
output_directory: results
bigquery:
gcp_project_id: !ENV ${EVAL_GCP_PROJECT_ID}
runners:
agent_runners: 1
Loading