Skip to content
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

Jump to bottom

Add options to populate meta data in wrappers foreach API request #86

Closed
ukclivecox opened this issue Feb 8, 2018 · 4 comments
Closed

Add options to populate meta data in wrappers foreach API request #86

ukclivecox opened this issue Feb 8, 2018 · 4 comments

Comments

@ukclivecox
Copy link
Contributor

  • Update python wrapper
@ukclivecox
Copy link
Contributor Author

At present the python wrapper does not allow people to pass back meta data.
We should add an option method say def meta() which if it exists is called and a user can pass back a dictionary of tags that will be placed in

seldon-core/proto/prediction.proto

Line 38 in 01a104c

map<string,google.protobuf.Value> tags = 2;

@ukclivecox
Copy link
Contributor Author

Each of the _microservice.py modules will need to be updated to add this functionality in https://github.com/SeldonIO/seldon-core/tree/master/wrappers/python

@hjarraya
Copy link

hjarraya commented Oct 25, 2018 •
edited
Loading

meta data should be added to the already existing ones.

@ukclivecox ukclivecox changed the title Add options to populate meta data in model wrapping Add options to populate meta data in wrappers foreach API request Oct 25, 2018
@ukclivecox
Copy link
Contributor Author

Available now.

agrski pushed a commit that referenced this issue Dec 2, 2022
@sakoush
Sherif akoush/scv2 50/flatten versions (and various other fixes) (#86)
29bb402 
* agent k6 testing helpers

* add agent testing scenario

* do not readd model to cache if error unload

* refactor test with setup and teardown

* increase setup timeout

* fetch model memory from agent state

* mlserver_exp1

* limit number of connections per host for rest rproxy

* add clients pool for reverse grpc proxy

* reduce number of models in test

* fix bug when mem is 0

* add grpc result

* tidy up protos

* failing test for memory calc

* try to lock model on evict

* add tx around evict

* add a test for evict transaction

* fix test and add EndEvict in interface

* integrate tx in state manager

* simple test to check models passed to mlserver

* fix lint and test

* remove unused func

* fix test

* add a delay

* tidy up test post merge

* remove extra check

* add helpers

* tests passing

* agent test changes

* fix to over commit notebook

* client tidy up

* wire up envoy

* rename Evict to StartEvict

* add grpc changes

* remove versions from incoming request from envoy

* remove version from grpc payload

* notebook changes (overcommit)

* changes for k6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hjarraya @ukclivecox