maybe we need this

.github/workflows/ci.yml

@@ -17,7 +17,52 @@ env:
   DEFAULT_PYTHON_VERSION: "3.11"
   NLTK_DATA: "/usr/share/nltk_data"
 jobs:
+  detect-duplicate:
+    name: Detect Duplicate Run
+    runs-on: ubuntu-24.04
+    outputs:
+      should_run: ${{ steps.check.outputs.should_run }}
+    steps:
+      - name: Check if workflow should run
+        id: check
+        uses: actions/github-script@v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            if (context.eventName !== 'push') {
+              core.info('Not a push event; running workflow.');
+              core.setOutput('should_run', 'true');
+              return;
+            }
+
+            const ref = context.ref || '';
+            if (!ref.startsWith('refs/heads/')) {
+              core.info('Push is not to a branch; running workflow.');
+              core.setOutput('should_run', 'true');
+              return;
+            }
+
+            const branch = ref.substring('refs/heads/'.length);
+            const { owner, repo } = context.repo;
+            const prs = await github.paginate(github.rest.pulls.list, {
+              owner,
+              repo,
+              state: 'open',
+              head: `${owner}:${branch}`,
+              per_page: 100,
+            });
+
+            if (prs.length === 0) {
+              core.info(`No open PR found for ${branch}; running workflow.`);
+              core.setOutput('should_run', 'true');
+            } else {
+              core.info(`Found ${prs.length} open PR(s) for ${branch}; skipping duplicate push run.`);
+              core.setOutput('should_run', 'false');
+            }
   pre-commit:
+    needs:
+      - detect-duplicate
+    if: needs.detect-duplicate.outputs.should_run == 'true'
     name: Linting Checks
     runs-on: ubuntu-24.04
     steps:
@@ -314,6 +359,10 @@ jobs:
     concurrency:
       group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
       cancel-in-progress: true
+    needs:
+      - tests-backend
+      - tests-frontend
+      - tests-frontend-e2e
     steps:
       - name: Prepare build variables
         id: build-vars
@@ -406,24 +455,6 @@ jobs:
           registry: quay.io
           username: ${{ secrets.QUAY_USERNAME }}
           password: ${{ secrets.QUAY_ROBOT_TOKEN }}
-      - name: Inspect cache/disk
-        if: always()
-        run: |
-          df -h
-          docker system df -v
-          docker buildx du
-      - name: Maximize space
-        run: |
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /opt/ghc
-          sudo rm -rf /usr/local/share/boost
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-      - name: Inspect cache/disk
-        if: always()
-        run: |
-          df -h
-          docker system df -v
-          docker buildx du
       - name: Build and push
         uses: docker/build-push-action@v6
         with:
@@ -445,12 +476,6 @@ jobs:
         if: steps.build-vars.outputs.can-push == 'true'
         run: |
           docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
-      - name: Inspect cache/disk
-        if: always()
-        run: |
-          df -h
-          docker system df -v
-          docker buildx du
       - name: Export frontend artifact from docker
         if: steps.build-vars.outputs.can-push == 'true'
         run: |

Dockerfile

@@ -193,13 +193,15 @@ ARG BUILD_PACKAGES="\
   pkg-config"
 
 # hadolint ignore=DL3042
-RUN set -eux \
+RUN --mount=type=cache,target=${UV_CACHE_DIR},id=python-cache \
+  set -eux \
   && echo "Installing build system packages" \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
   && echo "Installing Python requirements" \
     && uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt \
-    && uv pip install --system --no-python-downloads --python-preference system --requirements requirements.txt \
+    && UV_INDEX="https://pypi.org/simple https://download.pytorch.org/whl/cpu" UV_INDEX_STRATEGY=unsafe-best-match \
+       uv pip install --system --no-python-downloads --python-preference system --requirements requirements.txt \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \

pyproject.toml

@@ -75,6 +75,7 @@ dependencies = [
   "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
   "tika-client~=0.10.0",
+  "torch==2.7.0+cpu; sys_platform=='linux'",
   "tqdm~=4.67.1",
   "watchdog~=6.0",
   "whitenoise~=6.9",
@@ -172,8 +173,14 @@ psycopg-c = [
 ]
 tiktoken = { index = "pytorch-cpu" }
 tokenizers = { index = "pytorch-cpu" }
-torch = { index = "pytorch-cpu" }
+torch = [
-torchvision = { index = "pytorch-cpu" }
+  { index = "pytorch-cpu", marker = "sys_platform == 'linux'" },
+  { index = "pypi", marker = "sys_platform != 'linux'" },
+]
+torchvision = [
+  { index = "pytorch-cpu", marker = "sys_platform == 'linux'" },
+  { index = "pypi", marker = "sys_platform != 'linux'" },
+]
 zxing-cpp = [
   { url = "https://github.com/paperless-ngx/builder/releases/download/zxing-2.3.0/zxing_cpp-2.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
   { url = "https://github.com/paperless-ngx/builder/releases/download/zxing-2.3.0/zxing_cpp-2.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },