Create dockerfile

.dockerignore

@@ -1,6 +1,15 @@
-.venv
 .env
-**/.cache
 .git
-**/__pycache__
+__pycache__
+.cache
+.mypy_cache
+.pytest_cache
+.ipynb_checkpoints
+.gitignore
 .dockerignore
+Dockerfile
+.github
+.vscode
+docs
+scripts
+tests

.gitignore

@@ -5,6 +5,5 @@ __pycache__
 .cache
 .mypy_cache
 .pytest_cache
-**/.ipynb_checkpoints
-**/tracing_database.json
+.ipynb_checkpoints
 *.egg-info

Dockerfile

@@ -1,27 +1,26 @@
 FROM python:3.10.4-slim-bullseye
 
+LABEL org.opencontainers.image.title="GreatAI package wrapper container"
+LABEL org.opencontainers.image.vendor="ScoutinScience B.V."
+LABEL org.opencontainers.image.authors="andras@schmelczer.dev"
+LABEL org.opencontainers.image.source="https://github.com/ScoutinScience/great_ai"
+
 ENV ENVIRONMENT production
+EXPOSE 6060
 
-ARG ENTRYPOINT main.py
-
-WORKDIR /app
-
-RUN apt-get update &&\
-    apt-get install curl -y &&\
+RUN DEBIAN_FRONTEND=noninteractive apt update &&\
+    apt install curl -y &&\
     rm -rf /var/lib/apt/lists/*
 
-RUN pip install --no-cache-dir en-core-web-sm@https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.3.0/en_core_web_sm-3.3.0-py3-none-any.whl
-COPY great_ai great_ai
-RUN pip install --no-cache-dir ./great_ai
+COPY . great_ai
+RUN pip3 install --no-cache-dir ./great_ai &&\
+    rm -rf great_ai
 
-# COPY requirements.txt ./
-# RUN pip install --no-cache-dir --requirement requirements.txt
-
-COPY . .
-RUN rm -rf great_ai
-
-EXPOSE 6060
+RUN pip3 install --no-cache-dir en-core-web-sm@https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.3.0/en_core_web_sm-3.3.0-py3-none-any.whl
 
 HEALTHCHECK --interval=60s --timeout=60s --start-period=90s --retries=5 CMD [ "curl", "--fail", "http://localhost:6060/health" ]
 
-CMD ["great_ai", "$ENTRYPOINT"]
+WORKDIR /app
+VOLUME /app
+
+ENTRYPOINT ["/bin/sh", "python3", "-m", "great_ai"]

requirements.txt

@@ -1,23 +0,0 @@
-click < 8.1.0
-unidecode >= 1.3.0
-multiprocess >= 0.70.0.0
-tqdm >= 4.0.0
-psutil >= 5.9.0
-beautifulsoup4 >= 4.10.0
-lxml >= 4.6.0
-spacy >= 3.3.0
-pydantic >= 1.8.0
-scikit-learn == 1.1.1
-matplotlib >= 3.5.0
-numpy >= 1.22.0
-langcodes[data] >= 3.3.0
-segtok >= 1.5.11
-langdetect >= 1.0.9
-tinydb >= 4.7.0
-pandas >= 1.4.0
-pyaml >= 21.0.0
-boto3 >= 1.23.0
-fastapi >= 0.70.0
-plotly >= 5.8.0
-dash >= 2.4.0
-uvicorn[standard] >= 0.17.0