sdk-v2

Test Eval Case

Run one case through the full agent + judge path without saving a run.

The response is intentionally inline and ephemeral: no eval_runs or eval_case_results rows are created, so iterative case authoring does not pollute benchmark history or affect previous-run comparisons.

post/v2/sdk/eval-cases/{case_id}/test

Request

  • Base URL: https://api.pandas-ai.com (the document declares no server; this is the origin it was published from)
  • URL: https://api.pandas-ai.com/v2/sdk/eval-cases/{case_id}/test
  • Auth: none declared

Path parameters

case_idstring required

Request body

versionstring nullable

Semantic-layer version; default Current

tagsstring[] nullable

Selection tags (disambiguate entries)

languagestring nullable

Response language code, e.g. 'it'

disambiguationboolean

Expose structured ask questions (mirrors the SDK flag)

rowsinteger

Shadow rows per table

saltstring

Reroll the synthetic world

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.