drop python3.8 (#2372)

### Description
Remove all uses of python3.8

---------

Co-authored-by: ryannikolaidis <[email protected]>
Co-authored-by: rbiseck3 <[email protected]>

Author: rbiseck3

Diff for: .github/workflows/ci.yml

@@ -16,7 +16,7 @@ jobs:
   setup:
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -30,7 +30,7 @@ jobs:
   check-deps:
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
@@ -44,7 +44,7 @@ jobs:
   lint:
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
     runs-on: ubuntu-latest
@@ -84,7 +84,7 @@ jobs:
   test_unit:
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -150,7 +150,7 @@ jobs:
   test_unit_no_extras:
     strategy:
       matrix:
-        python-version: ["3.8"]
+        python-version: ["3.10"]
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -176,7 +176,7 @@ jobs:
     # NOTE(newelh) - Split extras into separate steps in the same pipeline (avoid using matrix)
     strategy:
       matrix:
-        python-version: ["3.8"]
+        python-version: ["3.10"]
         extra: ["csv", "docx", "odt", "markdown", "pypandoc", "msg", "pdf-image", "pptx", "xlsx"]
     runs-on: ubuntu-latest
     env:
@@ -218,7 +218,7 @@ jobs:
   setup_ingest:
     strategy:
       matrix:
-        python-version: [ "3.8","3.9","3.10","3.11" ]
+        python-version: [ "3.9","3.10","3.11" ]
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -232,7 +232,7 @@ jobs:
   test_ingest_unit:
     strategy:
       matrix:
-        python-version: [ "3.8","3.9","3.10","3.11" ]
+        python-version: [ "3.9","3.10","3.11" ]
     runs-on: ubuntu-latest
     needs: [ setup_ingest, lint ]
     steps:
@@ -258,7 +258,7 @@ jobs:
   test_ingest_src:
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     runs-on: ubuntu-latest-m
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -338,7 +338,7 @@ jobs:
     environment: ci
     strategy:
       matrix:
-        python-version: ["3.8","3.9","3.10","3.11"]
+        python-version: ["3.9","3.10","3.11"]
     runs-on: ubuntu-latest-m
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data
@@ -394,8 +394,8 @@ jobs:
   test_unstructured_api_unit:
     strategy:
       matrix:
-        # NOTE(yuming): Unstructured API only use Python 3.8
-        python-version: ["3.8"]
+        # NOTE(yuming): Unstructured API only use Python 3.10
+        python-version: ["3.10"]
     runs-on: ubuntu-latest
     env:
       NLTK_DATA: ${{ github.workspace }}/nltk_data

Diff for: .github/workflows/docker-publish.yml

@@ -9,7 +9,7 @@ env:
   DOCKER_REPOSITORY: quay.io/unstructured-io/unstructured
   DOCKER_BUILD_REPOSITORY: quay.io/unstructured-io/build-unstructured
   PIP_VERSION: "23.2.1"
-  PYTHON_VERSION: "3.8"
+  PYTHON_VERSION: "3.10"
 
 jobs:
   set-short-sha:

Diff for: CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.12.0
+
+### Enhancements
+
+* **Drop support for python3.8** All dependencies are now built off of the minimum version of python being `3.10`
+
 ## 0.11.9-dev4
 
 ### Enhancements

Diff for: docker/ubuntu-22/Dockerfile

@@ -13,7 +13,7 @@ COPY Makefile Makefile
 
 SHELL ["/bin/bash", "-c"]
 
-RUN source ~/.bashrc && pyenv virtualenv 3.8.17 unstructured && \
+RUN source ~/.bashrc && pyenv virtualenv 3.10 unstructured && \
     source ~/.pyenv/versions/unstructured/bin/activate && \
     make install-ci && \
     make install-ingest-s3 && \

Diff for: docs/requirements.txt

@@ -1,12 +1,12 @@
 #
-# This file is autogenerated by pip-compile with Python 3.8
+# This file is autogenerated by pip-compile with Python 3.9
 # by the following command:
 #
 #    pip-compile --output-file=build.txt build.in
 #
-alabaster==0.7.13
+alabaster==0.7.15
     # via sphinx
-babel==2.13.1
+babel==2.14.0
     # via sphinx
 beautifulsoup4==4.12.2
     # via
@@ -36,7 +36,7 @@ idna==3.6
     #   requests
 imagesize==1.4.1
     # via sphinx
-importlib-metadata==7.0.0
+importlib-metadata==7.0.1
     # via sphinx
 jinja2==3.1.2
     # via
@@ -63,8 +63,6 @@ pygments==2.17.2
     #   furo
     #   sphinx
     #   sphinx-tabs
-pytz==2023.3.post1
-    # via babel
 pyyaml==6.0.1
     # via myst-parser
 requests==2.31.0

Diff for: environment.yml

@@ -7,7 +7,7 @@ channels:
   - pytorch
 
 dependencies:
-  - python=3.8
+  - python=3.10
   - pytorch=1.12.1
   - pywin32
   - poppler

Diff for: examples/argilla-summarization/README.md

@@ -7,7 +7,7 @@ complete a data science project in hours that previously would have taken weeks.
 
 To get started, use the following steps:
 
-- Ensure you have Python 3.8 or higher installed on your system
+- Ensure you have Python 3.10 or higher installed on your system
 - Create a new Python virtual environment
 - Run `pip install -r requirements.txt` to install the dependencies
 - Run `PYTHONPATH=. jupyter notebook` from this directory to launch the notebook