feat(dataflow): Add pipeline version to Kafka headers #5493
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
Currently pipeline versions are not exposed via envoy when you send an inference request. This PR adds a
x-pipeline-version
to Kafka headers which is then picked up by envoy to return the pipeline information.Testing steps
Edit
seldonruntime
CR to specify the image:kengoa/seldon-dataflow-engine:5493
for dataflow engineFollowing the steps from https://github.com/SeldonIO/seldon-core/blob/v2/samples/pipeline-versions.md, with an additional argument
--show-headers
for theinfer
commands.After adding a pipeline with the
add10
model withseldon pipeline load -f ./pipelines/version-test-a.yaml
,it shows
x-pipeline-version: [1]
as expected.Applying
seldon pipeline load -f ./pipelines/version-test-b.yaml
with themul10
model and running the same infer command produces:which reflects the correct pipeline version with the right model name and output.
Which issue(s) this PR fixes:
Fixes #
Special notes for your reviewer: