chore: bump version to 0.16.0 [skip ci]

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

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

@@ -15,15 +15,23 @@ jobs:
         spec:
           - name: docling-project/docling-serve
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
+              UV_SYNC_EXTRA_ARGS=--no-extra flash-attn
             platforms: linux/amd64, linux/arm64
           - name: docling-project/docling-serve-cpu
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra flash-attn
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cpu --no-extra flash-attn
             platforms: linux/amd64, linux/arm64
           - name: docling-project/docling-serve-cu124
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cpu
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu124
+            platforms: linux/amd64
+          - name: docling-project/docling-serve-cu126
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu126
+            platforms: linux/amd64
+          - name: docling-project/docling-serve-cu128
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu128
             platforms: linux/amd64
 
     permissions:

.github/workflows/images.yml

@@ -19,15 +19,23 @@ jobs:
         spec:
           - name: docling-project/docling-serve
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
+              UV_SYNC_EXTRA_ARGS=--no-extra flash-attn
             platforms: linux/amd64, linux/arm64
           - name: docling-project/docling-serve-cpu
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra flash-attn
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cpu --no-extra flash-attn
             platforms: linux/amd64, linux/arm64
           - name: docling-project/docling-serve-cu124
             build_args: |
-              UV_SYNC_EXTRA_ARGS=--no-extra cpu
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu124
+            platforms: linux/amd64
+          - name: docling-project/docling-serve-cu126
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu126
+            platforms: linux/amd64
+          - name: docling-project/docling-serve-cu128
+            build_args: |
+              UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu128
             platforms: linux/amd64
 
     permissions:

.github/workflows/job-build.yml

@@ -17,7 +17,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
       - name: Install dependencies
-        run: uv sync --all-extras --no-extra cu124 --no-extra flash-attn
+        run: uv sync --all-extras --no-extra flash-attn
       - name: Build package
         run: uv build
       - name: Check content of wheel

.github/workflows/job-checks.yml

@@ -25,7 +25,7 @@ jobs:
           key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
 
       - name: Install dependencies
-        run: uv sync --frozen --all-extras --no-extra cu124 --no-extra flash-attn
+        run: uv sync --frozen --all-extras --no-extra flash-attn
 
       - name: Run styling check
         run: pre-commit run --all-files

.pre-commit-config.yaml

@@ -23,6 +23,6 @@ repos:
         files: '\.py$'
   - repo: https://github.com/astral-sh/uv-pre-commit
     # uv version.
-    rev: 0.6.1
+    rev: 0.7.13
     hooks:
       - id: uv-lock

CHANGELOG.md

@@ -1,3 +1,23 @@
+## [v0.16.0](https://github.com/docling-project/docling-serve/releases/tag/v0.16.0) - 2025-06-25
+
+### Feature
+
+* Package updates and more cuda images ([#229](https://github.com/docling-project/docling-serve/issues/229)) ([`30aca92`](https://github.com/docling-project/docling-serve/commit/30aca92298ab0d86bb4debcfcacb2dd8b9040a27))
+
+### Documentation
+
+* Update example resources and improve README ([#231](https://github.com/docling-project/docling-serve/issues/231)) ([`80755a7`](https://github.com/docling-project/docling-serve/commit/80755a7d5955f7d0c53df8e558fdd852dd1f5b75))
+
+## [v0.15.0](https://github.com/docling-project/docling-serve/releases/tag/v0.15.0) - 2025-06-17
+
+### Feature
+
+* Use redocs and scalar as api docs ([#228](https://github.com/docling-project/docling-serve/issues/228)) ([`873d05a`](https://github.com/docling-project/docling-serve/commit/873d05aefe141c63b9c1cf53b23b4fa8c96de05d))
+
+### Fix
+
+* "tesserocr" instead of "tesseract_cli" in usage docs ([#223](https://github.com/docling-project/docling-serve/issues/223)) ([`196c5ce`](https://github.com/docling-project/docling-serve/commit/196c5ce42a04d77234a4212c3d9b9772d2c2073e))
+
 ## [v0.14.0](https://github.com/docling-project/docling-serve/releases/tag/v0.14.0) - 2025-06-17
 
 ### Feature

Containerfile

@@ -42,7 +42,7 @@ ENV \
 
 ARG UV_SYNC_EXTRA_ARGS=""
 
-RUN --mount=from=ghcr.io/astral-sh/uv:0.6.1,source=/uv,target=/bin/uv \
+RUN --mount=from=ghcr.io/astral-sh/uv:0.7.13,source=/uv,target=/bin/uv \
     --mount=type=cache,target=/opt/app-root/src/.cache/uv,uid=1001 \
     --mount=type=bind,source=uv.lock,target=uv.lock \
     --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
@@ -61,7 +61,7 @@ RUN echo "Downloading models..." && \
     chmod -R g=u ${DOCLING_SERVE_ARTIFACTS_PATH}
 
 COPY --chown=1001:0 ./docling_serve ./docling_serve
-RUN --mount=from=ghcr.io/astral-sh/uv:0.6.1,source=/uv,target=/bin/uv \
+RUN --mount=from=ghcr.io/astral-sh/uv:0.7.13,source=/uv,target=/bin/uv \
     --mount=type=cache,target=/opt/app-root/src/.cache/uv,uid=1001 \
     --mount=type=bind,source=uv.lock,target=uv.lock \
     --mount=type=bind,source=pyproject.toml,target=pyproject.toml \

Makefile

@@ -26,26 +26,40 @@ md-lint-file:
 	$(CMD_PREFIX) touch .markdown-lint
 
 .PHONY: docling-serve-image
-docling-serve-image: Containerfile
+docling-serve-image: Containerfile ## Build docling-serve container image
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu" -f Containerfile -t ghcr.io/docling-project/docling-serve:$(TAG) .
+	$(CMD_PREFIX) docker build --load -f Containerfile -t ghcr.io/docling-project/docling-serve:$(TAG) .
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) ghcr.io/docling-project/docling-serve:$(BRANCH_TAG)
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) quay.io/docling-project/docling-serve:$(BRANCH_TAG)
 
 .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]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra flash-attn" -f Containerfile -t ghcr.io/docling-project/docling-serve-cpu:$(TAG) .
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-group pypi --group cpu --no-extra flash-attn" -f Containerfile -t ghcr.io/docling-project/docling-serve-cpu:$(TAG) .
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) ghcr.io/docling-project/docling-serve-cpu:$(BRANCH_TAG)
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) quay.io/docling-project/docling-serve-cpu:$(BRANCH_TAG)
 
 .PHONY: docling-serve-cu124-image
-docling-serve-cu124-image: Containerfile ## Build docling-serve container image with GPU support
+docling-serve-cu124-image: Containerfile ## Build docling-serve container image with CUDA 12.4 support
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve with Cuda 12.4]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cpu" -f Containerfile --platform linux/amd64 -t ghcr.io/docling-project/docling-serve-cu124:$(TAG) .
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu124" -f Containerfile --platform linux/amd64 -t ghcr.io/docling-project/docling-serve-cu124:$(TAG) .
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) ghcr.io/docling-project/docling-serve-cu124:$(BRANCH_TAG)
 	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) quay.io/docling-project/docling-serve-cu124:$(BRANCH_TAG)
 
+.PHONY: docling-serve-cu126-image
+docling-serve-cu126-image: Containerfile ## Build docling-serve container image with CUDA 12.6 support
+	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve with Cuda 12.6]"
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu126" -f Containerfile --platform linux/amd64 -t ghcr.io/docling-project/docling-serve-cu126:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu126:$(TAG) ghcr.io/docling-project/docling-serve-cu126:$(BRANCH_TAG)
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu126:$(TAG) quay.io/docling-project/docling-serve-cu126:$(BRANCH_TAG)
+
+.PHONY: docling-serve-cu128-image
+docling-serve-cu128-image: Containerfile ## Build docling-serve container image with CUDA 12.8 support
+	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve with Cuda 12.8]"
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-group pypi --group cu128" -f Containerfile --platform linux/amd64 -t ghcr.io/docling-project/docling-serve-cu128:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu128:$(TAG) ghcr.io/docling-project/docling-serve-cu128:$(BRANCH_TAG)
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu128:$(TAG) quay.io/docling-project/docling-serve-cu128:$(BRANCH_TAG)
+
 .PHONY: action-lint
 action-lint: .action-lint ##      Lint GitHub Action workflows
 .action-lint: $(shell find .github -type f) | action-lint-file
@@ -87,9 +101,9 @@ run-docling-cpu: ## Run the docling-serve container with CPU support and assign
 	$(ECHO_PREFIX) printf "  %-12s Running docling-serve container with CPU support on port 5001...\n" "[RUN CPU]"
 	$(CMD_PREFIX) docker run -it --name docling-serve-cpu -p 5001:5001 ghcr.io/docling-project/docling-serve-cpu:main
 
-.PHONY: run-docling-gpu
-run-docling-gpu: ## Run the docling-serve container with GPU support and assign a container name
+.PHONY: run-docling-cu124
+run-docling-cu124: ## Run the docling-serve container with GPU support and assign a container name
 	$(ECHO_PREFIX) printf "  %-12s Removing existing container if it exists...\n" "[CLEANUP]"
-	$(CMD_PREFIX) docker rm -f docling-serve-gpu 2>/dev/null || true
-	$(ECHO_PREFIX) printf "  %-12s Running docling-serve container with GPU support on port 5001...\n" "[RUN GPU]"
-	$(CMD_PREFIX) docker run -it --name docling-serve-gpu -p 5001:5001 ghcr.io/docling-project/docling-serve:main
+	$(CMD_PREFIX) docker rm -f docling-serve-cu124 2>/dev/null || true
+	$(ECHO_PREFIX) printf "  %-12s Running docling-serve container with GPU support on port 5001...\n" "[RUN CUDA 12.4]"
+	$(CMD_PREFIX) docker run -it --name docling-serve-cu124 -p 5001:5001 ghcr.io/docling-project/docling-serve-cu124:main

README.md

@@ -8,23 +8,31 @@
 
 Running [Docling](https://github.com/docling-project/docling) as an API service.
 
+📚 [Docling Serve documentation](./docs/README.md)
+
+- Learning how to [configure the webserver](./docs/configuration.md)
+- Get to know all [runtime options](./docs/usage.md) of the API
+- Explore usefule [deployment examples](./docs/deployment.md)
+- And more
+
 ## Getting started
 
 Install the `docling-serve` package and run the server.
 
 ```bash
 # Using the python package
-pip install "docling-serve"
-docling-serve run
+pip install "docling-serve[ui]"
+docling-serve run --enable-ui
 
 # Using container images, e.g. with Podman
-podman run -p 5001:5001 quay.io/docling-project/docling-serve
+podman run -p 5001:5001 -e DOCLING_SERVE_ENABLE_UI=1 quay.io/docling-project/docling-serve
 ```
 
 The server is available at
 
 - API <http://127.0.0.1:5001>
 - API documentation <http://127.0.0.1:5001/docs>
+- UI playground <http://127.0.0.1:5001/ui>
   ![swagger.png](img/swagger.png)
 
 Try it out with a simple conversion:
@@ -45,33 +53,22 @@ Available container images:
 
 | Name | Description | Arch | Size |
 | -----|-------------|------|------|
-| [`ghcr.io/docling-project/docling-serve`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve) <br /> [`quay.io/docling-project/docling-serve`](https://quay.io/repository/docling-project/docling-serve) | Simple image for Docling Serve, installing all packages from the official pypi.org index. | `linux/amd64`, `linux/arm64` | 3.6 GB |
+| [`ghcr.io/docling-project/docling-serve`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve) <br /> [`quay.io/docling-project/docling-serve`](https://quay.io/repository/docling-project/docling-serve) | Simple image for Docling Serve, installing all packages from the official pypi.org index. | `linux/amd64`, `linux/arm64` | 3.6 GB (arm64) <br /> 8.7 GB (amd64) |
 | [`ghcr.io/docling-project/docling-serve-cpu`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cpu) <br /> [`quay.io/docling-project/docling-serve-cpu`](https://quay.io/repository/docling-project/docling-serve-cpu) | Cpu-only image which installs `torch` from the pytorch cpu index. | `linux/amd64`, `linux/arm64` | 3.6 GB |
 | [`ghcr.io/docling-project/docling-serve-cu124`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cu124) <br /> [`quay.io/docling-project/docling-serve-cu124`](https://quay.io/repository/docling-project/docling-serve-cu124) | Cuda 12.4 image which installs `torch` from the pytorch cu124 index. | `linux/amd64` | 8.7 GB |
+| [`ghcr.io/docling-project/docling-serve-cu126`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cu126) <br /> [`quay.io/docling-project/docling-serve-cu126`](https://quay.io/repository/docling-project/docling-serve-cu126) | Cuda 12.6 image which installs `torch` from the pytorch cu126 index. | `linux/amd64` | 8.7 GB |
+| [`ghcr.io/docling-project/docling-serve-cu128`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cu128) <br /> [`quay.io/docling-project/docling-serve-cu128`](https://quay.io/repository/docling-project/docling-serve-cu128) | Cuda 12.8 image which installs `torch` from the pytorch cu128 index. | `linux/amd64` | 8.7 GB |
 
 Coming soon: `docling-serve-slim` images will reduce the size by skipping the model weights download.
 
 ### Demonstration UI
 
-```bash
-# Install the Python package with the extra dependencies
-pip install "docling-serve[ui]"
-docling-serve run --enable-ui
-
-# Run the container image with the extra env parameters
-podman run -p 5001:5001 -e DOCLING_SERVE_ENABLE_UI=true quay.io/docling-project/docling-serve
-```
-
 An easy to use UI is available at the `/ui` endpoint.
 
 ![ui-input.png](img/ui-input.png)
 
 ![ui-output.png](img/ui-output.png)
 
-## Documentation and advance usages
-
-Visit the [Docling Serve documentation](./docs/README.md) for learning how to [configure the webserver](./docs/configuration.md), use all the [runtime options](./docs/usage.md) of the API and [deployment examples](./docs/deployment.md), pre-load model weights into a persistent volume [model weights on persistent volume](./docs/pre-loading-models.md)
-
 ## Get help and support
 
 Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).

docling_serve/__main__.py

@@ -113,11 +113,13 @@ def _run(
     protocol = "https" if run_ssl else "http"
     url = f"{protocol}://{uvicorn_settings.host}:{uvicorn_settings.port}"
     url_docs = f"{url}/docs"
+    url_scalar = f"{url}/scalar"
     url_ui = f"{url}/ui"
 
     console.print("")
     console.print(f"Server started at [link={url}]{url}[/]")
     console.print(f"Documentation at [link={url_docs}]{url_docs}[/]")
+    console.print(f"Scalar docs at [link={url_docs}]{url_scalar}[/]")
     if docling_serve_settings.enable_ui:
         console.print(f"UI at [link={url_ui}]{url_ui}[/]")
 

docling_serve/app.py

@@ -25,6 +25,7 @@ from fastapi.openapi.docs import (
 )
 from fastapi.responses import RedirectResponse
 from fastapi.staticfiles import StaticFiles
+from scalar_fastapi import get_scalar_api_reference
 
 from docling.datamodel.base_models import DocumentStream
 
@@ -140,8 +141,8 @@ def create_app():  # noqa: C901
 
     app = FastAPI(
         title="Docling Serve",
-        docs_url=None if offline_docs_assets else "/docs",
-        redoc_url=None if offline_docs_assets else "/redocs",
+        docs_url=None if offline_docs_assets else "/swagger",
+        redoc_url=None if offline_docs_assets else "/docs",
         lifespan=lifespan,
         version=version,
     )
@@ -192,7 +193,7 @@ def create_app():  # noqa: C901
             name="static",
         )
 
-        @app.get("/docs", include_in_schema=False)
+        @app.get("/swagger", include_in_schema=False)
         async def custom_swagger_ui_html():
             return get_swagger_ui_html(
                 openapi_url=app.openapi_url,
@@ -206,7 +207,7 @@ def create_app():  # noqa: C901
         async def swagger_ui_redirect():
             return get_swagger_ui_oauth2_redirect_html()
 
-        @app.get("/redoc", include_in_schema=False)
+        @app.get("/docs", include_in_schema=False)
         async def redoc_html():
             return get_redoc_html(
                 openapi_url=app.openapi_url,
@@ -214,6 +215,15 @@ def create_app():  # noqa: C901
                 redoc_js_url="/static/redoc.standalone.js",
             )
 
+    @app.get("/scalar", include_in_schema=False)
+    async def scalar_html():
+        return get_scalar_api_reference(
+            openapi_url=app.openapi_url,
+            title=app.title,
+            scalar_favicon_url="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg",
+            # hide_client_button=True,  # not yet released but in main
+        )
+
     ########################
     # Async / Sync helpers #
     ########################

docling_serve/datamodel/convert.py

@@ -8,8 +8,8 @@ from docling.datamodel.base_models import InputFormat, OutputFormat
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     PdfBackend,
-    PdfPipeline,
     PictureDescriptionBaseOptions,
+    ProcessingPipeline,
     TableFormerMode,
     TableStructureOptions,
 )
@@ -132,7 +132,11 @@ class ConvertDocumentsOptions(BaseModel):
                 f"Allowed values: {', '.join([v.value for v in OutputFormat])}. "
                 "Optional, defaults to Markdown."
             ),
-            examples=[[OutputFormat.MARKDOWN]],
+            examples=[
+                [OutputFormat.MARKDOWN],
+                [OutputFormat.MARKDOWN, OutputFormat.JSON],
+                [v.value for v in OutputFormat],
+            ],
         ),
     ] = [OutputFormat.MARKDOWN]
 
@@ -223,15 +227,15 @@ class ConvertDocumentsOptions(BaseModel):
     ] = TableStructureOptions().mode
 
     pipeline: Annotated[
-        PdfPipeline,
+        ProcessingPipeline,
         Field(description="Choose the pipeline to process PDF or image files."),
-    ] = PdfPipeline.STANDARD
+    ] = ProcessingPipeline.STANDARD
 
     page_range: Annotated[
         PageRange,
         Field(
             description="Only convert a range of pages. The page number starts at 1.",
-            examples=[(1, 4)],
+            examples=[DEFAULT_PAGE_RANGE, (1, 4)],
         ),
     ] = DEFAULT_PAGE_RANGE
 

docling_serve/docling_conversion.py

@@ -19,10 +19,10 @@ from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     OcrOptions,
     PdfBackend,
-    PdfPipeline,
     PdfPipelineOptions,
     PictureDescriptionApiOptions,
     PictureDescriptionVlmOptions,
+    ProcessingPipeline,
     TableFormerMode,
     VlmPipelineOptions,
     smoldocling_vlm_conversion_options,
@@ -217,7 +217,7 @@ def get_pdf_pipeline_opts(
         )
 
     pipeline_options: Union[PdfPipelineOptions, VlmPipelineOptions]
-    if request.pipeline == PdfPipeline.STANDARD:
+    if request.pipeline == ProcessingPipeline.STANDARD:
         pipeline_options = _parse_standard_pdf_opts(request, artifacts_path)
         backend = _parse_backend(request)
         pdf_format_option = PdfFormatOption(
@@ -225,7 +225,7 @@ def get_pdf_pipeline_opts(
             backend=backend,
         )
 
-    elif request.pipeline == PdfPipeline.VLM:
+    elif request.pipeline == ProcessingPipeline.VLM:
         pipeline_options = _parse_vlm_pdf_opts(request, artifacts_path)
         pdf_format_option = PdfFormatOption(
             pipeline_cls=VlmPipeline, pipeline_options=pipeline_options

docling_serve/gradio_ui.py

@@ -16,7 +16,7 @@ import httpx
 from docling.datamodel.base_models import FormatToExtensions
 from docling.datamodel.pipeline_options import (
     PdfBackend,
-    PdfPipeline,
+    ProcessingPipeline,
     TableFormerMode,
     TableStructureOptions,
 )
@@ -587,9 +587,9 @@ with gr.Blocks(
         with gr.Row():
             with gr.Column(scale=1, min_width=200):
                 pipeline = gr.Radio(
-                    [(v.value.capitalize(), v.value) for v in PdfPipeline],
+                    [(v.value.capitalize(), v.value) for v in ProcessingPipeline],
                     label="Pipeline type",
-                    value=PdfPipeline.STANDARD.value,
+                    value=ProcessingPipeline.STANDARD.value,
                 )
         with gr.Row():
             with gr.Column(scale=1, min_width=200):

docling_serve/helper_functions.py

@@ -36,7 +36,7 @@ def FormDepends(cls: type[BaseModel]):
         annotation = model_field.annotation
         description = model_field.description
         default = (
-            Form(..., description=description)
+            Form(..., description=description, examples=model_field.examples)
             if model_field.is_required()
             else Form(
                 model_field.default,

docs/configuration.md

@@ -60,7 +60,7 @@ The selected compute engine will be running all the async jobs.
 
 #### Local engine
 
-The following table describes the options to configure the Docling Serve KFP engine.
+The following table describes the options to configure the Docling Serve local engine.
 
 | ENV | Default | Description |
 |-----|---------|-------------|

docs/deploy-examples/docling-model-cache-deployment.yaml

@@ -22,8 +22,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 2
+              memory: 4Gi
             requests:
               cpu: 250m
               memory: 1Gi

docs/deploy-examples/docling-serve-oauth.yaml

@@ -85,7 +85,7 @@ spec:
           resources:
             limits:
               cpu: 2000m
-              memory: 2Gi
+              memory: 4Gi
             requests:
               cpu: 800m
               memory: 1Gi

docs/deploy-examples/docling-serve-replicas-w-sticky-sessions.yaml

@@ -60,8 +60,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 1
+              memory: 4Gi
             requests:
               cpu: 250m
               memory: 1Gi

docs/deploy-examples/docling-serve-simple.yaml

@@ -40,8 +40,8 @@ spec:
         - name: api
           resources:
             limits:
-              cpu: 500m
-              memory: 2Gi
+              cpu: 1
+              memory: 4Gi
               nvidia.com/gpu: 1  # Limit to one GPU
             requests:
               cpu: 250m

docs/usage.md

@@ -13,7 +13,7 @@ On top of the source of file (see below), both endpoints support the same parame
 - `do_ocr` (bool): If enabled, the bitmap content will be processed using OCR. Defaults to `True`.
 - `image_export_mode`: Image export mode for the document (only in case of JSON, Markdown or HTML). Allowed values: embedded, placeholder, referenced. Optional, defaults to `embedded`.
 - `force_ocr` (bool): If enabled, replace any existing text with OCR-generated text over the full content. Defaults to `False`.
-- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesseract_cli`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`.
+- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesserocr`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`. To use the `tesserocr` engine, `tesserocr` must be installed where docling-serve is running: `pip install tesserocr`
 - `ocr_lang` (List[str]): List of languages used by the OCR engine. Note that each OCR engine has different values for the language names. Defaults to empty.
 - `pdf_backend` (str): PDF backend to use. Allowed values: `pypdfium2`, `dlparse_v1`, `dlparse_v2`, `dlparse_v4`. Defaults to `dlparse_v4`.
 - `table_mode` (str): Table mode to use. Allowed values: `fast`, `accurate`. Defaults to `fast`.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.14.0"  # DO NOT EDIT, updated automatically
+version = "0.16.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [
@@ -26,11 +26,15 @@ classifiers = [
     # "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Developers",
     "Typing :: Typed",
-    "Programming Language :: Python :: 3"
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
 ]
 requires-python = ">=3.10"
 dependencies = [
-    "docling[vlm]~=2.28",
+    "docling[vlm]~=2.38",
     "docling-core>=2.32.0",
     "mlx-vlm~=0.1.12; sys_platform == 'darwin' and platform_machine == 'arm64'",
     "fastapi[standard]~=0.115",
@@ -42,6 +46,7 @@ dependencies = [
     "typer~=0.12",
     "uvicorn[standard]>=0.29.0,<1.0.0",
     "websockets~=14.0",
+    "scalar-fastapi>=1.0.3",
 ]
 
 [project.optional-dependencies]
@@ -56,14 +61,6 @@ rapidocr = [
     "rapidocr-onnxruntime~=1.4; python_version<'3.13'",
     "onnxruntime~=1.7",
 ]
-cpu = [
-  "torch>=2.6.0",
-  "torchvision>=0.21.0",
-]
-cu124 = [
-  "torch>=2.6.0",
-  "torchvision>=0.21.0",
-]
 flash-attn = [
   "flash-attn~=2.7.0; sys_platform == 'linux' and platform_machine == 'x86_64'"
 ]
@@ -79,18 +76,39 @@ dev = [
     "python-semantic-release~=7.32",
     "ruff>=0.9.6",
 ]
+pypi = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]
+cpu = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]
+cu124 = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]
+cu126 = [
+  "torch>=2.6.0",
+  "torchvision>=0.21.0",
+]
+cu128 = [
+  "torch>=2.7.0",
+  "torchvision>=0.22.0",
+]
 
 [tool.uv]
 package = true
+default-groups = ["dev", "pypi"]
 conflicts = [
   [
-    { extra = "cpu" },
-    { extra = "cu124" },
+    { group = "pypi" },
+    { group = "cpu" },
+    { group = "cu124" },
+    { group = "cu126" },
+    { group = "cu128" },
   ],
-  [
-    { extra = "cpu" },
-    { extra = "flash-attn" },
-  ],]
+]
 environments = ["sys_platform != 'darwin' or platform_machine != 'x86_64'"]
 override-dependencies = [
   "urllib3~=2.0"
@@ -98,14 +116,25 @@ override-dependencies = [
 
 [tool.uv.sources]
 torch = [
-  { index = "pytorch-cpu", extra = "cpu" },
-  { index = "pytorch-cu124", extra = "cu124" },
+  { index = "pytorch-pypi", group = "pypi" },
+  { index = "pytorch-cpu", group = "cpu" },
+  { index = "pytorch-cu124", group = "cu124" },
+  { index = "pytorch-cu126", group = "cu126" },
+  { index = "pytorch-cu128", group = "cu128" },
 ]
 torchvision = [
-  { index = "pytorch-cpu", extra = "cpu" },
-  { index = "pytorch-cu124", extra = "cu124" },
+  { index = "pytorch-pypi", group = "pypi" },
+  { index = "pytorch-cpu", group = "cpu" },
+  { index = "pytorch-cu124", group = "cu124" },
+  { index = "pytorch-cu126", group = "cu126" },
+  { index = "pytorch-cu128", group = "cu128" },
 ]
 
+[[tool.uv.index]]
+name = "pytorch-pypi"
+url = "https://pypi.org/simple"
+explicit = true
+
 [[tool.uv.index]]
 name = "pytorch-cpu"
 url = "https://download.pytorch.org/whl/cpu"
@@ -116,6 +145,16 @@ name = "pytorch-cu124"
 url = "https://download.pytorch.org/whl/cu124"
 explicit = true
 
+[[tool.uv.index]]
+name = "pytorch-cu126"
+url = "https://download.pytorch.org/whl/cu126"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch-cu128"
+url = "https://download.pytorch.org/whl/cu128"
+explicit = true
+
 [tool.setuptools.packages.find]
 include = ["docling_serve*"]
 namespaces = true
@@ -213,6 +252,7 @@ module = [
     "kfp.*",
     "kfp_server_api.*",
     "mlx_vlm.*",
+    "scalar_fastapi.*",
 ]
 ignore_missing_imports = true