chore: bump version to 0.4.0 [skip ci]

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

.github/workflows/ci-images-dryrun.yml

@@ -8,8 +8,24 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  build_cpu_image:
-    name: Build docling-serve "CPU only" container image
+  build_image:
+    name: Build ${{ matrix.spec.name }} container image
+    strategy:
+      matrix:
+        spec:
+          - name: ds4sd/docling-serve
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
+            platforms: linux/amd64, linux/arm64
+          - name: ds4sd/docling-serve-cpu
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cu124
+            platforms: linux/amd64, linux/arm64
+          - name: ds4sd/docling-serve-cu124
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cpu
+            platforms: linux/amd64
+
     permissions:
       packages: write
       contents: read
@@ -19,25 +35,7 @@ jobs:
     uses: ./.github/workflows/job-image.yml
     with:
       publish: false
-      build_args: |
-        UV_SYNC_EXTRA_ARGS=--no-extra cu124
-      ghcr_image_name: ds4sd/docling-serve-cpu
-      quay_image_name: ""
-
-
-  build_gpu_image:
-    name: Build docling-serve (with GPU support) container image
-    permissions:
-      packages: write
-      contents: read
-      attestations: write
-      id-token: write
-
-    uses: ./.github/workflows/job-image.yml
-    with:
-      publish: false
-      build_args: |
-        UV_SYNC_EXTRA_ARGS=--no-extra cpu
-      platforms: linux/amd64
-      ghcr_image_name: ds4sd/docling-serve
+      build_args: ${{ matrix.spec.build_args }}
+      ghcr_image_name: ${{ matrix.spec.name }}
       quay_image_name: ""
+      platforms: ${{ matrix.spec.platforms }}

.github/workflows/images.yml

@@ -4,24 +4,32 @@ on:
   push:
     branches:
       - main
-    tags:
-      - 'v*'
-
-# env:
-#   GHCR_REGISTRY: ghcr.io
-#   # GHCR_DOCLING_SERVE_CPU_IMAGE_NAME: ds4sd/docling-serve-cpu
-#   # GHCR_DOCLING_SERVE_GPU_IMAGE_NAME: ds4sd/docling-serve
-#   QUAY_REGISTRY: quay.io
-#   # QUAY_DOCLING_SERVE_CPU_IMAGE_NAME: ds4sd/docling-serve-cpu
-#   # QUAY_DOCLING_SERVE_GPU_IMAGE_NAME: ds4sd/docling-serve
+  release:
+    types: [published]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
 jobs:
-  build_and_publish_cpu_images:
-    name: Push docling-serve "CPU only" container image to GHCR and QUAY
+  build_and_publish_images:
+    name: Build and push ${{ matrix.spec.name }} container image to GHCR and QUAY
+    strategy:
+      matrix:
+        spec:
+          - name: ds4sd/docling-serve
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
+            platforms: linux/amd64, linux/arm64
+          - name: ds4sd/docling-serve-cpu
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cu124
+            platforms: linux/amd64, linux/arm64
+          - name: ds4sd/docling-serve-cu124
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-extra cpu
+            platforms: linux/amd64
+
     permissions:
       packages: write
       contents: read
@@ -33,28 +41,7 @@ jobs:
     with:
       publish: true
       environment: registry-creds
-      build_args: |
-        UV_SYNC_EXTRA_ARGS=--no-extra cu124
-      ghcr_image_name: ds4sd/docling-serve-cpu
-      quay_image_name: ds4sd/docling-serve-cpu
-
-
-  build_and_publish_gpu_images:
-    name: Push docling-serve (with GPU support) container image to GHCR and QUAY
-    permissions:
-      packages: write
-      contents: read
-      attestations: write
-      id-token: write
-    secrets: inherit
-
-    uses: ./.github/workflows/job-image.yml
-    with:
-      publish: true
-      environment: registry-creds
-      build_args: |
-        UV_SYNC_EXTRA_ARGS=--no-extra cpu
-      platforms: linux/amd64
-      ghcr_image_name: ds4sd/docling-serve
-      quay_image_name: ds4sd/docling-serve
-
+      build_args: ${{ matrix.spec.build_args }}
+      ghcr_image_name: ${{ matrix.spec.name }}
+      quay_image_name: ${{ matrix.spec.name }}
+      platforms: ${{ matrix.spec.platforms }}

.github/workflows/job-image.yml

@@ -28,11 +28,7 @@ on:
 
 env:
   GHCR_REGISTRY: ghcr.io
-  # GHCR_DOCLING_SERVE_CPU_IMAGE_NAME: ds4sd/docling-serve-cpu
-  # GHCR_DOCLING_SERVE_GPU_IMAGE_NAME: ds4sd/docling-serve
   QUAY_REGISTRY: quay.io
-  # QUAY_DOCLING_SERVE_CPU_IMAGE_NAME: ds4sd/docling-serve-cpu
-  # QUAY_DOCLING_SERVE_GPU_IMAGE_NAME: ds4sd/docling-serve
 
 jobs:
   image:
@@ -135,6 +131,10 @@ jobs:
           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: |

CHANGELOG.md

@@ -1,3 +1,10 @@
+## [v0.4.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.4.0) - 2025-02-26
+
+### Feature
+
+* New container images ([#68](https://github.com/DS4SD/docling-serve/issues/68)) ([`7e6d9cd`](https://github.com/DS4SD/docling-serve/commit/7e6d9cdef398df70a5b4d626aeb523c428c10d56))
+* Render DoclingDocument with npm docling-components in the example UI ([#65](https://github.com/DS4SD/docling-serve/issues/65)) ([`c430d9b`](https://github.com/DS4SD/docling-serve/commit/c430d9b1a162ab29104d86ebaa1ac5a5488b1f09))
+
 ## [v0.3.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.3.0) - 2025-02-19
 
 ### Feature

Makefile

@@ -24,6 +24,13 @@ action-lint-file:
 md-lint-file:
 	$(CMD_PREFIX) touch .markdown-lint
 
+.PHONY: docling-serve-image
+docling-serve-image: Containerfile
+	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve]"
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu" -f Containerfile -t ghcr.io/ds4sd/docling-serve:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) ghcr.io/ds4sd/docling-serve:main
+	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) quay.io/ds4sd/docling-serve:main
+
 .PHONY: docling-serve-cpu-image
 docling-serve-cpu-image: Containerfile ## Build docling-serve "cpu only" container image
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve CPU]"
@@ -31,12 +38,12 @@ docling-serve-cpu-image: Containerfile ## Build docling-serve "cpu only" contain
 	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cpu:$(TAG) ghcr.io/ds4sd/docling-serve-cpu:main
 	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cpu:$(TAG) quay.io/ds4sd/docling-serve-cpu:main
 
-.PHONY: docling-serve-gpu-image
-docling-serve-gpu-image: Containerfile ## Build docling-serve container image with GPU support
-	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve with GPU]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cpu" -f Containerfile --platform linux/amd64 -t ghcr.io/ds4sd/docling-serve:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) ghcr.io/ds4sd/docling-serve:main
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) quay.io/ds4sd/docling-serve:main
+.PHONY: docling-serve-cu124-image
+docling-serve-cu124-image: Containerfile ## Build docling-serve container image with GPU support
+	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve with Cuda 12.4]"
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cpu" -f Containerfile --platform linux/amd64 -t ghcr.io/ds4sd/docling-serve-cu124:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cu124:$(TAG) ghcr.io/ds4sd/docling-serve-cu124:main
+	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cu124:$(TAG) quay.io/ds4sd/docling-serve-cu124:main
 
 .PHONY: action-lint
 action-lint: .action-lint ##      Lint GitHub Action workflows

README.md

@@ -276,6 +276,17 @@ The response can be a JSON Document or a File.
 - If you set the parameter `return_as_file` to True, the response will be a zip file.
 - If multiple files are generated (multiple inputs, or one input but multiple outputs with `return_as_file` True), the response will be a zip file.
 
+## Run docling-serve
+
+Clone the repository and run the following from within the cloned directory root.
+
+```bash
+python -m venv venv
+source venv/bin/activate
+pip install "docling-serve[ui]"
+docling-serve run --enable-ui
+```
+
 ## Helpers
 
 - A full Swagger UI is available at the `/docs` endpoint.
@@ -323,7 +334,7 @@ uv sync --extra ui --extra rapidocr
 uv sync --extra tesserocr
 ```
 
-See `[project.optional-dependencies]` section in `pyproject.toml` for full list of options.
+See `[project.optional-dependencies]` section in `pyproject.toml` for full list of options and runtime options with `uv run docling-serve --help`.
 
 ### Run the server
 

docling_serve/gradio_ui.py

@@ -12,6 +12,13 @@ from docling_serve.helper_functions import _to_list_of_strings
 
 logger = logging.getLogger(__name__)
 
+##############################
+# Head JS for web components #
+##############################
+head = """
+    <script src="https://unpkg.com/@docling/docling-components@0.0.3" type="module"></script>
+"""
+
 #################
 # CSS and theme #
 #################
@@ -49,6 +56,14 @@ css = """
 #file_input_zone {
     height: 140px;
 }
+
+docling-img::part(pages) {
+    gap: 1rem;
+}
+
+docling-img::part(page) {
+    box-shadow: 0 0.5rem 1rem 0 rgba(0, 0, 0, 0.2);
+}
 """
 
 theme = gr.themes.Default(
@@ -110,6 +125,7 @@ def set_download_button_label(label_text: gr.State):
 def clear_outputs():
     markdown_content = ""
     json_content = ""
+    json_rendered_content = ""
     html_content = ""
     text_content = ""
     doctags_content = ""
@@ -118,6 +134,7 @@ def clear_outputs():
         markdown_content,
         markdown_content,
         json_content,
+        json_rendered_content,
         html_content,
         html_content,
         text_content,
@@ -260,6 +277,7 @@ def process_file(
 def response_to_output(response, return_as_file):
     markdown_content = ""
     json_content = ""
+    json_rendered_content = ""
     html_content = ""
     text_content = ""
     doctags_content = ""
@@ -282,6 +300,12 @@ def response_to_output(response, return_as_file):
         json_content = json.dumps(
             full_content.get("document").get("json_content"), indent=2
         )
+        # Embed document JSON and trigger load at client via an image.
+        json_rendered_content = f"""
+            <docling-img id="dclimg" pagenumbers tooltip="parsed"></docling-img>
+            <script id="dcljson" type="application/json" onload="document.getElementById('dclimg').src = JSON.parse(document.getElementById('dcljson').textContent);">{json_content}</script>
+            <img src onerror="document.getElementById('dclimg').src = JSON.parse(document.getElementById('dcljson').textContent);" />
+            """
         html_content = full_content.get("document").get("html_content")
         text_content = full_content.get("document").get("text_content")
         doctags_content = full_content.get("document").get("doctags_content")
@@ -289,6 +313,7 @@ def response_to_output(response, return_as_file):
         markdown_content,
         markdown_content,
         json_content,
+        json_rendered_content,
         html_content,
         html_content,
         text_content,
@@ -302,6 +327,7 @@ def response_to_output(response, return_as_file):
 ############
 
 with gr.Blocks(
+    head=head,
     css=css,
     theme=theme,
     title="Docling Serve",
@@ -464,6 +490,8 @@ with gr.Blocks(
             output_markdown_rendered = gr.Markdown(label="Response")
         with gr.Tab("Docling (JSON)"):
             output_json = gr.Code(language="json", wrap_lines=True, show_label=False)
+        with gr.Tab("Docling-Rendered"):
+            output_json_rendered = gr.HTML()
         with gr.Tab("HTML"):
             output_html = gr.Code(language="html", wrap_lines=True, show_label=False)
         with gr.Tab("HTML-Rendered"):
@@ -514,6 +542,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,
@@ -538,6 +567,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,
@@ -553,6 +583,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,
@@ -582,6 +613,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,
@@ -606,6 +638,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,
@@ -621,6 +654,7 @@ with gr.Blocks(
             output_markdown,
             output_markdown_rendered,
             output_json,
+            output_json_rendered,
             output_html,
             output_html_rendered,
             output_text,

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.3.0"  # DO NOT EDIT, updated automatically
+version = "0.4.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [