mlflow: [BUG]

System information

• Have I written custom code (as opposed to using a stock example script provided in MLflow): custom model training script
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 16.04 in Docker container
• MLflow installed from (source or binary): source (mlflow repository, master branch)
• MLflow version (run mlflow --version): 1.3.1.dev0
• Python version: 3.7.3
• npm version, if running the dev UI: 3.10.10
• Exact command to reproduce: docker-compose up

Describe the problem

1. On open some run in mlflow ui:

2019/10/22 10:20:08 ERROR mlflow.server: Exception on /ajax-api/2.0/preview/mlflow/model-versions/search [GET]
 Traceback (most recent call last):
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/app.py", line 2446, in wsgi_app
     response = self.full_dispatch_request()
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/app.py", line 1951, in full_dispatch_request
     rv = self.handle_user_exception(e)
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/app.py", line 1820, in handle_user_exception
     reraise(exc_type, exc_value, tb)
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/_compat.py", line 39, in reraise
     raise value
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/app.py", line 1949, in full_dispatch_request
     rv = self.dispatch_request()
   File "/usr/local/lib/python3.7/site-packages/Flask-1.1.1-py3.7.egg/flask/app.py", line 1935, in dispatch_request
     return self.view_functions[rule.endpoint](**req.view_args)
   File "/usr/local/lib/python3.7/site-packages/mlflow-1.3.1.dev0-py3.7.egg/mlflow/server/handlers.py", line 137, in wrapper
     return func(*args, **kwargs)
   File "/usr/local/lib/python3.7/site-packages/mlflow-1.3.1.dev0-py3.7.egg/mlflow/server/handlers.py", line 581, in _search_model_versions
     model_versions_detailed = _get_model_registry_store().search_model_versions(
 AttributeError: 'NoneType' object has no attribute 'search_model_versions'

1. On click Register Model:

Code to reproduce issue

Project sources mlflow_model_registry.zip

Archive content:

I. Dockerfile

FROM python
WORKDIR /home

# RUN pip install sklearn git+https://github.com/mparkhe/mlflow.git@ssue-19
RUN apt-get update && \
    curl -sL https://deb.nodesource.com/setup_6.x | bash - && \
    apt-get update && \
    apt-get install -y nodejs npm

RUN pip install sklearn

RUN git clone https://github.com/mlflow/mlflow && \
    cd mlflow && python setup.py install && \
    cd mlflow/server/js && npm install

ENV MLFLOW_TRACKING_URI=/home/mlruns

CMD mlflow server --host 0.0.0.0 --port 5000 & (cd mlflow/mlflow/server/js && npm start)

II. docker-compose.yml

version: '3'

services:
  mlflow_model_registry:
    build:
      context: .

    image: mlflow_model_registry:latest

    container_name: mlflow_model_registry_1

    ports:
      - 5000:5000
      - 3000:3000

    volumes:
      - ./main.py:/home/main.py
      - ./mlruns:/home/mlruns

III. main.py

import joblib
import mlflow
from mlflow.sklearn import log_model
from sklearn import svm
from sklearn import datasets


clf = svm.SVC(gamma='scale')
iris = datasets.load_iris()
X, y = iris.data, iris.target
clf.fit(X, y)

joblib.dump(clf, 'iris.model')

log_model('iris.model', 'model')

Run all:

1. build image and run container

docker-compose build
docker-compose up

1. enter docker container in new terminal window

docker exec -ti mlflow_model_registry_1 /bin/bash

1. run training script

python main.py

1. open dev UI