Closed deepankarm closed 9 months ago
Attention: 46 lines
in your changes are missing coverage. Please review.
Comparison is base (
4ea8bb5
) 76.93% compared to head (9ff2d57
) 76.85%.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
can u add tests with docker?
Added - https://github.com/jina-ai/jina/pull/6055/commits/a7faa6f412742605ee9af43232c66db9b2175dd5
Goals
PR in continuation to https://github.com/jina-ai/jina/pull/6046.
Sagemaker still calls the
POST /invocations
route during batch-transform but with different content-type & body. To enable bothapplication/json
(for inference) andtext/csv
(for batch-transform, I removed the pydantic model from the path signature, rather use fastapi'sRequest
class and evaluate the body according to the content-type.For batch-transform,
text/csv
orapplication/csv
content type.input_model
(user-defined model in the Executor route).Gotchas
Rows in the input csv should have all fields defined in the input type (including optional fields like
id
)Following inputs are valid
Following CSV is invalid.
End-to-end tests
I've manually tested the Executor after pushing a model to S3, the Executor image to ECR & running batch-transform jobs for both
SingleLine
andMultiLine
records.