Comments (3)
Thank you for reporting us your feedback!
The internal ticket has been created: https://warthogs.atlassian.net/browse/KF-5135.
This message was autogenerated
from seldonio-rocks.
mlserver-sklearn
Adding this in this ROCK's command also resulted in the following errors
╰─$ kl sklearn-default-0-classifier-864547595b-m68nw
Defaulted container "classifier" out of: classifier, seldon-container-engine, classifier-model-initializer (init)
2023-12-13T11:48:50.028Z [pebble] Started daemon.
2023-12-13T11:48:50.032Z [pebble] POST /v1/services 3.575839ms 202
2023-12-13T11:48:50.032Z [pebble] Started default services with change 1.
2023-12-13T11:48:50.035Z [pebble] Service "mlserver-sklearn" starting: bash -c 'export PATH=/opt/conda/bin/:/opt/mlserver/.local/bin:${PATH}:/usr/bin && export PYTHONPATH=/opt/mlserver/.local/lib/python3.8/site-packages/:${PYTHONPATH} && eval $(/opt/conda/bin/conda shell.bash hook 2> /dev/null) && source /hack/activate-env.sh ${MLSERVER_ENV_TARBALL} && mlserver start ${MLSERVER_MODELS_DIR}'
2023-12-13T11:48:50.329Z [mlserver-sklearn] Environment tarball not found at '/mnt/models/environment.tar.gz'
2023-12-13T11:48:50.329Z [mlserver-sklearn] Environment not found at './envs/environment'
2023-12-13T11:48:51.631Z [mlserver-sklearn] Traceback (most recent call last):
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/bin/mlserver", line 8, in <module>
2023-12-13T11:48:51.631Z [mlserver-sklearn] sys.exit(main())
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/cli/main.py", line 263, in main
2023-12-13T11:48:51.631Z [mlserver-sklearn] root()
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/click/core.py", line 1157, in __call__
2023-12-13T11:48:51.631Z [mlserver-sklearn] return self.main(*args, **kwargs)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/click/core.py", line 1078, in main
2023-12-13T11:48:51.631Z [mlserver-sklearn] rv = self.invoke(ctx)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/click/core.py", line 1688, in invoke
2023-12-13T11:48:51.631Z [mlserver-sklearn] return _process_result(sub_ctx.command.invoke(sub_ctx))
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/click/core.py", line 1434, in invoke
2023-12-13T11:48:51.631Z [mlserver-sklearn] return ctx.invoke(self.callback, **ctx.params)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/click/core.py", line 783, in invoke
2023-12-13T11:48:51.631Z [mlserver-sklearn] return __callback(*args, **kwargs)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/cli/main.py", line 23, in wrapper
2023-12-13T11:48:51.631Z [mlserver-sklearn] return asyncio.run(f(*args, **kwargs))
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/conda/lib/python3.8/asyncio/runners.py", line 44, in run
2023-12-13T11:48:51.631Z [mlserver-sklearn] return loop.run_until_complete(main)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/cli/main.py", line 46, in start
2023-12-13T11:48:51.631Z [mlserver-sklearn] server = MLServer(settings)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/server.py", line 32, in __init__
2023-12-13T11:48:51.631Z [mlserver-sklearn] self._metrics_server = MetricsServer(self._settings)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/metrics/server.py", line 25, in __init__
2023-12-13T11:48:51.631Z [mlserver-sklearn] self._app = self._get_app()
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/mlserver/metrics/server.py", line 28, in _get_app
2023-12-13T11:48:51.631Z [mlserver-sklearn] app = FastAPI(debug=self._settings.debug)
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/fastapi/applications.py", line 146, in __init__
2023-12-13T11:48:51.631Z [mlserver-sklearn] self.middleware_stack: ASGIApp = self.build_middleware_stack()
2023-12-13T11:48:51.631Z [mlserver-sklearn] File "/opt/mlserver/.local/lib/python3.8/site-packages/fastapi/applications.py", line 152, in build_middleware_stack
2023-12-13T11:48:51.631Z [mlserver-sklearn] debug = self.debug
2023-12-13T11:48:51.631Z [mlserver-sklearn] AttributeError: 'FastAPI' object has no attribute 'debug'
2023-12-13T11:48:51.771Z [pebble] Service "mlserver-sklearn" stopped unexpectedly with code 1
2023-12-13T11:48:51.771Z [pebble] Service "mlserver-sklearn" on-failure action is "restart", waiting ~500ms before restart (backoff 1)
Maybe there is something I miss from those ROCKs design and we indeed do not need this because we 're already running in the proper environment.
EDIT: Turns out that the above doesn't have to do with activating the environment
from seldonio-rocks.
The above issue doesn't stand anymore. This was caused by the fact that running rockcraft clean && rockcraft pack
with the rockcraft.yaml pack didn't result in the same dependencies in the built images (as described in #80 (comment)). With that being said, we indeed removed the source /hack/activate-env.sh ${MLSERVER_ENV_TARBALL}
part of the command due to #37 (comment).
from seldonio-rocks.
Related Issues (20)
- sklearn-server ROCK should implement a second Dockerfile too HOT 4
- MLServer ROCK discrepancies HOT 2
- sklearnserver ROCK technical implementation HOT 2
- Workflows are needed for this repository HOT 1
- Update rockraft file of mlserver-mlflow for CKF 1.8 HOT 2
- Update rockraft file of mlserver-xgboost for CKF 1.8 HOT 2
- Update rockraft file of mlserver-sklearn for CKF 1.8 HOT 2
- Update rockraft file of mlserver-huggingface for CKF 1.8
- Update rockraft file of seldon-core-operator for CKF 1.8
- Update rockraft file of jupyter-scipy for CKF 1.8
- Update rockraft file of sklearnserver for CKF 1.8 HOT 2
- Introduce ROCK automations for building and pushing ROCKs
- Add `mlserver` ROCK to `build_and_scan_rocks` workflow HOT 1
- Document how `mlserver-*` images are built upstream
- `mlserver-mlflow` ROCK returns response in different format than upstream during integration tests
- `mlserver-*` fail to start with "'FastAPI' object has no attribute 'debug'" HOT 2
- tensorflow-serving ROCK integration tests fail HOT 1
- tensorflow-serving rounds up results differently than upstream HOT 5
- fix tensorflow-serving rock's default args HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from seldonio-rocks.