ci: workflow improvements

.github/scripts/release.sh

@@ -3,38 +3,74 @@
 set -e  # trigger failure on error - do not remove!
 set -x  # display command on output
 
+## debug
+# TARGET_VERSION="1.2.x"
+
 if [ -z "${TARGET_VERSION}" ]; then
     >&2 echo "No TARGET_VERSION specified"
     exit 1
 fi
 CHGLOG_FILE="${CHGLOG_FILE:-CHANGELOG.md}"
 
-# update package version
+# Update package version
 uvx --from=toml-cli toml set --toml-path=pyproject.toml project.version "${TARGET_VERSION}"
 uv lock --upgrade-package docling-serve
 
-# collect release notes
+# Extract all docling packages and versions from uv.lock
+DOCVERSIONS=$(uvx --with toml python3 - <<'PY'
+import toml
+data = toml.load("uv.lock")
+for pkg in data.get("package", []):
+    if pkg["name"].startswith("docling"):
+        print(f"{pkg['name']} {pkg['version']}")
+PY
+)
+
+# Format docling versions list without trailing newline
+DOCLING_VERSIONS="### Docling libraries included in this release:"
+while IFS= read -r line; do
+  DOCLING_VERSIONS+="
+- $line"
+done <<< "$DOCVERSIONS"
+
+# Collect release notes
 REL_NOTES=$(mktemp)
 uv run --no-sync semantic-release changelog --unreleased >> "${REL_NOTES}"
 
-# update changelog
+# Strip trailing blank lines from release notes and append docling versions
+{
+  sed -e :a -e '/^\n*$/{$d;N;};/\n$/ba' "${REL_NOTES}"
+  printf "\n"
+  printf "%s" "${DOCLING_VERSIONS}"
+  printf "\n"
+} > "${REL_NOTES}.tmp" && mv "${REL_NOTES}.tmp" "${REL_NOTES}"
+
+# Update changelog
 TMP_CHGLOG=$(mktemp)
 TARGET_TAG_NAME="v${TARGET_VERSION}"
 RELEASE_URL="$(gh repo view --json url -q ".url")/releases/tag/${TARGET_TAG_NAME}"
-printf "## [${TARGET_TAG_NAME}](${RELEASE_URL}) - $(date -Idate)\n\n" >> "${TMP_CHGLOG}"
-cat "${REL_NOTES}" >> "${TMP_CHGLOG}"
-if [ -f "${CHGLOG_FILE}" ]; then
-    printf "\n" | cat - "${CHGLOG_FILE}" >> "${TMP_CHGLOG}"
-fi
+## debug
+#RELEASE_URL="myrepo/releases/tag/${TARGET_TAG_NAME}"
+
+# Strip leading blank lines from existing changelog to avoid multiple blank lines when appending
+EXISTING_CL=$(sed -e :a -e '/^\n*$/{$d;N;};/\n$/ba' "${CHGLOG_FILE}")
+
+{
+  printf "## [${TARGET_TAG_NAME}](${RELEASE_URL}) - $(date -Idate)\n\n"
+  cat "${REL_NOTES}"
+  printf "\n"
+  printf "%s\n" "${EXISTING_CL}"
+} >> "${TMP_CHGLOG}"
+
 mv "${TMP_CHGLOG}" "${CHGLOG_FILE}"
 
-# push changes
+# Push changes
 git config --global user.name 'github-actions[bot]'
 git config --global user.email 'github-actions[bot]@users.noreply.github.com'
 git add pyproject.toml uv.lock "${CHGLOG_FILE}"
 COMMIT_MSG="chore: bump version to ${TARGET_VERSION} [skip ci]"
 git commit -m "${COMMIT_MSG}"
 git push origin main
 
-# create GitHub release (incl. Git tag)
+# Create GitHub release (incl. Git tag)
 gh release create "${TARGET_TAG_NAME}" -F "${REL_NOTES}"

.github/workflows/job-image.yml

@@ -93,7 +93,7 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           context: .
-          push: ${{ inputs.publish }}
+          push: ${{ inputs.publish }} # set false for local test
           tags: ${{ steps.ghcr_meta.outputs.tags }}
           labels: ${{ steps.ghcr_meta.outputs.labels }}
           platforms: ${{ inputs.platforms}}
@@ -123,19 +123,217 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           context: .
-          push: ${{ inputs.publish }}
+          push: ${{ inputs.publish }} # set false for local test
           tags: ${{ steps.quay_meta.outputs.tags }}
           labels: ${{ steps.quay_meta.outputs.labels }}
           platforms: ${{ inputs.platforms}}
           cache-from: type=gha
           cache-to: type=gha,mode=max
           file: Containerfile
           build-args: ${{ inputs.build_args }}
-      
+
       # - name: Inspect the image details
       #   run: |
       #     echo "${{ steps.ghcr_push.outputs.metadata }}"
 
       - name: Remove Local Docker Images
         run: |
           docker image prune -af
+
+      # - name: Set metadata outputs for local testing, and comment out buildx, cache, metadata
+      #   id: ghcr_meta
+      #   run: |
+      #     echo "tags=ghcr.io/docling-project/docling-serve-cpu:main" >> $GITHUB_OUTPUT
+      #     echo "labels=org.opencontainers.image.source=https://github.com/docling-project/docling-serve" >> $GITHUB_OUTPUT
+
+    outputs:
+      image-tags: ${{ steps.ghcr_meta.outputs.tags }}
+      image-labels: ${{ steps.ghcr_meta.outputs.labels }}
+
+  test-cpu-image:
+    needs:
+      - image
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: read
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Test CPU images
+        run: |
+          set -e
+
+          echo "Testing image: ${{ needs.image.outputs.image-tags }}"
+
+          for tag in ${{ needs.image.outputs.image-tags }}; do
+            if echo "$tag" | grep -q -- '-cpu' && echo "$tag" | grep -qE ':[vV][0-9]+(\.[0-9]+){0,2}$'; then
+              echo "Testing CPU image: $tag"
+
+              # Remove existing container if any
+              docker rm -f docling-serve-test-container 2>/dev/null || true
+
+              echo "Pulling image..."
+              docker pull "$tag"
+
+              echo "Waiting 5s after pull..."
+              sleep 5
+
+              echo "Starting container..."
+              docker run -d -p 5001:5001 --name docling-serve-test-container "$tag"
+
+              echo "Waiting 15s for container to boot..."
+              sleep 15
+
+              echo "Checking service health..."
+              for i in {1..20}; do
+                health_response=$(curl -s http://localhost:5001/health || true)
+                echo "Health check response [$i]: $health_response"
+                if echo "$health_response" | grep -q '"status":"ok"'; then
+                  echo "Service is healthy!"
+                  echo "Sending test conversion request..."
+
+                  status_code=$(curl -s -o /dev/null -w "%{http_code}" -X POST 'http://localhost:5001/v1/convert/source' \
+                    -H 'accept: application/json' \
+                    -H 'Content-Type: application/json' \
+                    -d '{
+                      "options": {
+                        "from_formats": ["pdf"],
+                        "to_formats": ["md"]
+                      },
+                      "sources": [
+                        {
+                          "kind": "http",
+                          "url": "https://arxiv.org/pdf/2501.17887"
+                        }
+                      ],
+                      "target": {
+                        "kind": "inbody"
+                      }
+                    }')
+
+                  echo "Conversion request returned status code: $status_code"
+
+                  if [ "$status_code" -ne 200 ]; then
+                    echo "Conversion failed!"
+                    docker logs docling-serve-test-container
+                    docker rm -f docling-serve-test-container
+                    exit 1
+                  fi
+
+                  break
+                else
+                  echo "Waiting for service... [$i/20]"
+                  sleep 3
+                fi
+              done
+
+              if ! echo "$health_response" | grep -q '"status":"ok"'; then
+                echo "Service did not become healthy in time."
+                docker logs docling-serve-test-container
+                docker rm -f docling-serve-test-container
+                exit 1
+              fi
+
+              echo "Cleaning up test container..."
+              docker rm -f docling-serve-test-container
+            else
+              echo "Skipping non-released or non-CPU image: $tag"
+            fi
+          done
+
+  test-cuda-image:
+    needs:
+      - image
+    runs-on: ubuntu-latest # >> placeholder for GPU runner << #
+    permissions:
+      contents: read
+      packages: read
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Test CUDA images
+        run: |
+          set -e
+
+          echo "Testing image: ${{ needs.image.outputs.image-tags }}"
+
+          for tag in ${{ needs.image.outputs.image-tags }}; do
+            if echo "$tag" | grep -qE -- '-cu[0-9]+' && echo "$tag" | grep -qE ':[vV][0-9]+(\.[0-9]+){0,2}$'; then
+              echo "Testing CUDA image: $tag"
+
+              # Remove existing container if any
+              docker rm -f docling-serve-test-container 2>/dev/null || true
+
+              echo "Pulling image..."
+              docker pull "$tag"
+
+              echo "Waiting 5s after pull..."
+              sleep 5
+
+              echo "Starting container..."
+              docker run -d -p 5001:5001 --gpus all --name docling-serve-test-container "$tag"
+
+              echo "Waiting 15s for container to boot..."
+              sleep 15
+
+              echo "Checking service health..."
+              for i in {1..25}; do
+                health_response=$(curl -s http://localhost:5001/health || true)
+                echo "Health check response [$i]: $health_response"
+                if echo "$health_response" | grep -q '"status":"ok"'; then
+                  echo "Service is healthy!"
+                  echo "Sending test conversion request..."
+
+                  status_code=$(curl -s -o /dev/null -w "%{http_code}" -X POST 'http://localhost:5001/v1/convert/source' \
+                    -H 'accept: application/json' \
+                    -H 'Content-Type: application/json' \
+                    -d '{
+                      "options": {
+                        "from_formats": ["pdf"],
+                        "to_formats": ["md"]
+                      },
+                      "sources": [
+                        {
+                          "kind": "http",
+                          "url": "https://arxiv.org/pdf/2501.17887"
+                        }
+                      ],
+                      "target": {
+                        "kind": "inbody"
+                      }
+                    }')
+
+                  echo "Conversion request returned status code: $status_code"
+
+                  if [ "$status_code" -ne 200 ]; then
+                    echo "Conversion failed!"
+                    docker logs docling-serve-test-container
+                    docker rm -f docling-serve-test-container
+                    exit 1
+                  fi
+
+                  break
+                else
+                  echo "Waiting for service... [$i/25]"
+                  sleep 3
+                fi
+              done
+
+              if ! echo "$health_response" | grep -q '"status":"ok"'; then
+                echo "Service did not become healthy in time."
+                docker logs docling-serve-test-container
+                docker rm -f docling-serve-test-container
+                exit 1
+              fi
+
+              echo "Cleaning up test container..."
+              docker rm -f docling-serve-test-container
+            else
+              echo "Skipping non-released or non-CUDA image: $tag"
+            fi
+          done