Bump Python to 3.11, rebuild deps, revert CI changes

Author: PastelStorm

.github/workflows/ci.yml

@@ -7,7 +7,7 @@ on:
     branches: [ main ]
 
 env:
-  PYTHON_VERSION: "3.10"
+  PYTHON_VERSION: "3.12"
   PIPELINE_FAMILY: "general"
 
 jobs:
@@ -20,7 +20,7 @@ jobs:
       with:
         path: |
           .venv
-        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/base.txt', 'requirements/test.txt') }}
+        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/*.txt') }}
     - name: Set up Python ${{ env.PYTHON_VERSION }}
       uses: actions/setup-python@v5
       with:
@@ -42,7 +42,7 @@ jobs:
       with:
         path: |
           .venv
-        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/base.txt', 'requirements/test.txt') }}
+        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/*.txt') }}
     - name: Lint
       run: |
         source .venv/bin/activate
@@ -65,11 +65,13 @@ jobs:
       with:
         path: |
           .venv
-        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/base.txt', 'requirements/test.txt') }}
+        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/test.txt') }}
     - name: Run core tests
       run: |
+        python${{ env.PYTHON_VERSION }} -m venv .venv
         source .venv/bin/activate
         sudo apt-get update && sudo apt-get install --yes poppler-utils libreoffice
+        make install-test
         make install-pandoc
         sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5
         sudo apt-get install -y tesseract-ocr tesseract-ocr-kor
@@ -105,9 +107,11 @@ jobs:
       with:
         path: |
           .venv
-        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/base.txt', 'requirements/test.txt') }}
+        key: ci-venv-${{ env.PIPELINE_FAMILY }}-${{ hashFiles('requirements/test.txt') }}
     - name: Test Dockerfile
       run: |
+        python${{ env.PYTHON_VERSION }} -m venv .venv
+        make install-test
         source .venv/bin/activate
         make docker-build
         make docker-test

.github/workflows/docker-publish.yml

@@ -11,7 +11,7 @@ env:
   PACKAGE: "unstructured-api"
   PIPELINE_FAMILY: "general"
   PIP_VERSION: "25.1.1"
-  PYTHON_VERSION: "3.10"
+  PYTHON_VERSION: "3.12"
 
 jobs:
   setup:

Dockerfile

@@ -1,13 +1,19 @@
 # syntax=docker/dockerfile:experimental
-FROM quay.io/unstructured-io/base-images:wolfi-base-latest as base
+FROM quay.io/unstructured-io/base-images:wolfi-py3.12-slim-latest as base
 
 # NOTE(crag): NB_USER ARG for mybinder.org compat:
 #             https://mybinder.readthedocs.io/en/latest/tutorials/dockerfile.html
 ARG NB_USER=notebook-user
 ARG NB_UID=1000
 ARG PIP_VERSION
 ARG PIPELINE_PACKAGE
-ARG PYTHON_VERSION="3.11"
+ARG PYTHON_VERSION="3.12"
+
+USER root
+
+RUN apk add --no-cache shadow \
+ && useradd -m -u ${NB_UID} -s /bin/sh ${NB_USER}
+RUN chown -R ${NB_USER}:${NB_USER} ${HOME}
 
 # Set up environment
 ENV PYTHON python${PYTHON_VERSION}

README.md

@@ -289,12 +289,13 @@ curl -X 'POST'
 * Using `pyenv` to manage virtualenv's is recommended
 	* Mac install instructions. See [here](https://github.com/Unstructured-IO/community#mac--homebrew) for more detailed instructions.
 		* `brew install pyenv-virtualenv`
-	  * `pyenv install 3.10.12`
+	  * `pyenv install 3.12.11`
   * Linux instructions are available [here](https://github.com/Unstructured-IO/community#linux).
 
   * Create a virtualenv to work in and activate it, e.g. for one named `document-processing`:
 
-	`pyenv  virtualenv 3.10.12 unstructured-api` <br />
+	`pyenv  virtualenv 3.12.11
+   unstructured-api` <br />
 	`pyenv activate unstructured-api`
 
 See the [Unstructured Quick Start](https://github.com/Unstructured-IO/unstructured#eight_pointed_black_star-quick-start) for the many OS dependencies that are required, if the ability to process all file types is desired.

requirements/base.in

@@ -1,9 +1,6 @@
 -c constraints.in
 unstructured[all-docs]
-# Pinning click due to a unicode issue in black
-# can remove after black drops support for Python 3.6
-# ref: https://github.com/psf/black/issues/2964
-click==8.2.1
+click
 fastapi
 uvicorn
 ratelimit