chore: bump version to 0.8.0 [skip ci]

feat: Add option for vlm pipeline (#143 )
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2025-11-29 08:33:50 +00:00 · 2025-04-22 13:04:33 +00:00 · 2025-04-22 14:46:33 +02:00 · 2025-04-22 10:41:47 +02:00 · 2025-04-19 19:59:07 +02:00 · 2025-04-19 18:46:28 +02:00
16 changed files with 3496 additions and 1936 deletions
--- a/.markdownlint-cli2.yaml
+++ b/.markdownlint-cli2.yaml
@@ -3,7 +3,7 @@ config:
  no-emphasis-as-header: false
  first-line-heading: false
  MD033:
-    allowed_elements: ["details", "summary", "br", "a", "p", "img"]
+    allowed_elements: ["details", "summary", "br", "a", "b", "p", "img"]
  MD024:
    siblings_only: true
 globs:
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,23 @@
+## [v0.8.0](https://github.com/docling-project/docling-serve/releases/tag/v0.8.0) - 2025-04-22
+
+### Feature
+
+* Add option for vlm pipeline ([#143](https://github.com/docling-project/docling-serve/issues/143)) ([`ee89ee4`](https://github.com/docling-project/docling-serve/commit/ee89ee4daee5e916bd6a3bdb452f78934cd03f60))
+* Expose more conversion options ([#142](https://github.com/docling-project/docling-serve/issues/142)) ([`6b3d281`](https://github.com/docling-project/docling-serve/commit/6b3d281f02905c195ab75f25bb39f5c4d4e7b680))
+* **UI:** Change UI to use async endpoints ([#131](https://github.com/docling-project/docling-serve/issues/131)) ([`b598872`](https://github.com/docling-project/docling-serve/commit/b598872e5c48928ac44417a11bb7acc0e5c3f0c6))
+
+### Fix
+
+* **UI:** Use https when calling the api ([#139](https://github.com/docling-project/docling-serve/issues/139)) ([`57f9073`](https://github.com/docling-project/docling-serve/commit/57f9073bc0daf72428b068ea28e2bec7cd76c37b))
+* Fix permissions in docker image ([#136](https://github.com/docling-project/docling-serve/issues/136)) ([`c1ce471`](https://github.com/docling-project/docling-serve/commit/c1ce4719c933179ba3c59d73d0584853bbd6fa6a))
+* Picture caption visuals ([#129](https://github.com/docling-project/docling-serve/issues/129)) ([`5dfb75d`](https://github.com/docling-project/docling-serve/commit/5dfb75d3b9a7022d1daad12edbb8ec7bbf9aa264))
+
+### Documentation
+
+* Fix required permissions for oauth2-proxy requests ([#141](https://github.com/docling-project/docling-serve/issues/141)) ([`087417e`](https://github.com/docling-project/docling-serve/commit/087417e5c2387d4ed95500222058f34d8a8702aa))
+* Update deployment examples ([#135](https://github.com/docling-project/docling-serve/issues/135)) ([`525a43f`](https://github.com/docling-project/docling-serve/commit/525a43ff6f04b7cc80f9dd6a0e653a8d8c4ab317))
+* Fix image tag ([#124](https://github.com/docling-project/docling-serve/issues/124)) ([`420162e`](https://github.com/docling-project/docling-serve/commit/420162e674cc38b4c3c13673ffbee4c20a1b15f1))
+
 ## [v0.7.0](https://github.com/docling-project/docling-serve/releases/tag/v0.7.0) - 2025-03-31

 ### Feature
--- a/10
+++ b/10
@@ -17,6 +17,8 @@ RUN --mount=type=bind,source=os-packages.txt,target=/tmp/os-packages.txt \
    dnf -y clean all && \
    rm -rf /var/cache/dnf

+RUN /usr/bin/fix-permissions /opt/app-root/src/.cache
+
 ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/

 ###################################################################################################
@@ -44,7 +46,7 @@ RUN --mount=from=ghcr.io/astral-sh/uv:0.6.1,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 \
-    uv sync --frozen --no-install-project --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}
+    umask 002 && uv sync --frozen --no-install-project --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}

 ARG MODELS_LIST="layout tableformer picture_classifier easyocr"

@@ -52,15 +54,15 @@ RUN echo "Downloading models..." && \
    HF_HUB_DOWNLOAD_TIMEOUT="90" \
    HF_HUB_ETAG_TIMEOUT="90" \
    docling-tools models download -o "${DOCLING_SERVE_ARTIFACTS_PATH}" ${MODELS_LIST} && \
-    chown -R 1001:0 /opt/app-root/src/.cache && \
-    chmod -R g=u /opt/app-root/src/.cache
+    chown -R 1001:0 ${DOCLING_SERVE_ARTIFACTS_PATH} && \
+    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 \
    --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 \
-    uv sync --frozen --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}
+    umask 002 && uv sync --frozen --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}

 EXPOSE 5001

--- a/13
+++ b/13
@@ -17,6 +17,7 @@ else
 endif

 TAG=$(shell git rev-parse HEAD)
+BRANCH_TAG=$(shell git rev-parse --abbrev-ref HEAD)

 action-lint-file:
 	$(CMD_PREFIX) touch .action-lint
@@ -28,22 +29,22 @@ md-lint-file:
 docling-serve-image: Containerfile
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve]"
 	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu" -f Containerfile -t ghcr.io/docling-project/docling-serve:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) ghcr.io/docling-project/docling-serve:main
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) quay.io/docling-project/docling-serve:main
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(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]"
 	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124" -f Containerfile -t ghcr.io/docling-project/docling-serve-cpu:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) ghcr.io/docling-project/docling-serve-cpu:main
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) quay.io/docling-project/docling-serve-cpu:main
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(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
 	$(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) .
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) ghcr.io/docling-project/docling-serve-cu124:main
-	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) quay.io/docling-project/docling-serve-cu124:main
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(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: action-lint
 action-lint: .action-lint ##      Lint GitHub Action workflows
--- a/docling_serve/datamodel/convert.py
+++ b/docling_serve/datamodel/convert.py
@@ -7,7 +7,13 @@ from docling.datamodel.base_models import InputFormat, OutputFormat
 from docling.datamodel.pipeline_options import (
    EasyOcrOptions,
    PdfBackend,
+    PdfPipeline,
    TableFormerMode,
+    TableStructureOptions,
+)
+from docling.datamodel.settings import (
+    DEFAULT_PAGE_RANGE,
+    PageRange,
 )
 from docling.models.factories import get_ocr_factory
 from docling_core.types.doc import ImageRefMode
@@ -121,16 +127,37 @@ class ConvertDocumentsOptions(BaseModel):
    table_mode: Annotated[
        TableFormerMode,
        Field(
-            TableFormerMode.FAST,
            description=(
                "Mode to use for table structure, String. "
                f"Allowed values: {', '.join([v.value for v in TableFormerMode])}. "
                "Optional, defaults to fast."
            ),
-            examples=[TableFormerMode.FAST],
+            examples=[TableStructureOptions().mode],
            # pattern="fast|accurate",
        ),
-    ] = TableFormerMode.FAST
+    ] = TableStructureOptions().mode
+
+    pipeline: Annotated[
+        PdfPipeline,
+        Field(description="Choose the pipeline to process PDF or image files."),
+    ] = PdfPipeline.STANDARD
+
+    page_range: Annotated[
+        PageRange,
+        Field(
+            description="Only convert a range of pages. The page number starts at 1.",
+            examples=[(1, 4)],
+        ),
+    ] = DEFAULT_PAGE_RANGE
+
+    document_timeout: Annotated[
+        float,
+        Field(
+            description="The timeout for processing each document, in seconds.",
+            gt=0,
+            le=docling_serve_settings.max_document_timeout,
+        ),
+    ] = docling_serve_settings.max_document_timeout

    abort_on_error: Annotated[
        bool,
--- a/docling_serve/docling_conversion.py
+++ b/docling_serve/docling_conversion.py
@@ -1,6 +1,7 @@
 import hashlib
 import json
 import logging
+import sys
 from collections.abc import Iterable, Iterator
 from functools import lru_cache
 from pathlib import Path
@@ -18,10 +19,15 @@ from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
    OcrOptions,
    PdfBackend,
+    PdfPipeline,
    PdfPipelineOptions,
    TableFormerMode,
+    VlmPipelineOptions,
+    smoldocling_vlm_conversion_options,
+    smoldocling_vlm_mlx_conversion_options,
 )
 from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
+from docling.pipeline.vlm_pipeline import VlmPipeline
 from docling_core.types.doc import ImageRefMode

 from docling_serve.datamodel.convert import ConvertDocumentsOptions, ocr_factory
@@ -84,10 +90,9 @@ def get_converter(pdf_format_option: PdfFormatOption) -> DocumentConverter:
    return _get_converter_from_hash(options_hash)


-# Computes the PDF pipeline options and returns the PdfFormatOption and its hash
-def get_pdf_pipeline_opts(
-    request: ConvertDocumentsOptions,
-) -> PdfFormatOption:
+def _parse_standard_pdf_opts(
+    request: ConvertDocumentsOptions, artifacts_path: Optional[Path]
+) -> PdfPipelineOptions:
    try:
        ocr_options: OcrOptions = ocr_factory.create_options(
            kind=request.ocr_engine.value,  # type: ignore
@@ -110,6 +115,8 @@ def get_pdf_pipeline_opts(
            ocr_options.lang = request.ocr_lang

    pipeline_options = PdfPipelineOptions(
+        artifacts_path=artifacts_path,
+        document_timeout=request.document_timeout,
        do_ocr=request.do_ocr,
        ocr_options=ocr_options,
        do_table_structure=request.do_table_structure,
@@ -118,7 +125,6 @@ def get_pdf_pipeline_opts(
        do_picture_classification=request.do_picture_classification,
        do_picture_description=request.do_picture_description,
    )
-    pipeline_options.table_structure_options.do_cell_matching = True  # do_cell_matching
    pipeline_options.table_structure_options.mode = TableFormerMode(request.table_mode)

    if request.image_export_mode != ImageRefMode.PLACEHOLDER:
@@ -126,6 +132,10 @@ def get_pdf_pipeline_opts(
        if request.images_scale:
            pipeline_options.images_scale = request.images_scale

+    return pipeline_options
+
+
+def _parse_backend(request: ConvertDocumentsOptions) -> type[PdfDocumentBackend]:
    if request.pdf_backend == PdfBackend.DLPARSE_V1:
        backend: type[PdfDocumentBackend] = DoclingParseDocumentBackend
    elif request.pdf_backend == PdfBackend.DLPARSE_V2:
@@ -137,35 +147,78 @@ def get_pdf_pipeline_opts(
    else:
        raise RuntimeError(f"Unexpected PDF backend type {request.pdf_backend}")

+    return backend
+
+
+def _parse_vlm_pdf_opts(
+    request: ConvertDocumentsOptions, artifacts_path: Optional[Path]
+) -> VlmPipelineOptions:
+    pipeline_options = VlmPipelineOptions(
+        artifacts_path=artifacts_path,
+        document_timeout=request.document_timeout,
+    )
+    pipeline_options.vlm_options = smoldocling_vlm_conversion_options
+    if sys.platform == "darwin":
+        try:
+            import mlx_vlm  # noqa: F401
+
+            pipeline_options.vlm_options = smoldocling_vlm_mlx_conversion_options
+        except ImportError:
+            _log.warning(
+                "To run SmolDocling faster, please install mlx-vlm:\n"
+                "pip install mlx-vlm"
+            )
+    return pipeline_options
+
+
+# Computes the PDF pipeline options and returns the PdfFormatOption and its hash
+def get_pdf_pipeline_opts(
+    request: ConvertDocumentsOptions,
+) -> PdfFormatOption:
+    artifacts_path: Optional[Path] = None
    if docling_serve_settings.artifacts_path is not None:
        if str(docling_serve_settings.artifacts_path.absolute()) == "":
            _log.info(
                "artifacts_path is an empty path, model weights will be dowloaded "
                "at runtime."
            )
-            pipeline_options.artifacts_path = None
+            artifacts_path = None
        elif docling_serve_settings.artifacts_path.is_dir():
            _log.info(
                "artifacts_path is set to a valid directory. "
                "No model weights will be downloaded at runtime."
            )
-            pipeline_options.artifacts_path = docling_serve_settings.artifacts_path
+            artifacts_path = docling_serve_settings.artifacts_path
        else:
            _log.warning(
                "artifacts_path is set to an invalid directory. "
                "The system will download the model weights at runtime."
            )
-            pipeline_options.artifacts_path = None
+            artifacts_path = None
    else:
        _log.info(
            "artifacts_path is unset. "
            "The system will download the model weights at runtime."
        )

-    pdf_format_option = PdfFormatOption(
-        pipeline_options=pipeline_options,
-        backend=backend,
-    )
+    pipeline_options: Union[PdfPipelineOptions, VlmPipelineOptions]
+    if request.pipeline == PdfPipeline.STANDARD:
+        pipeline_options = _parse_standard_pdf_opts(request, artifacts_path)
+        backend = _parse_backend(request)
+        pdf_format_option = PdfFormatOption(
+            pipeline_options=pipeline_options,
+            backend=backend,
+        )
+
+    elif request.pipeline == PdfPipeline.VLM:
+        pipeline_options = _parse_vlm_pdf_opts(request, artifacts_path)
+        pdf_format_option = PdfFormatOption(
+            pipeline_cls=VlmPipeline, pipeline_options=pipeline_options
+        )
+    else:
+        raise NotImplementedError(
+            f"The pipeline {request.pipeline} is not implemented."
+        )

    return pdf_format_option

@@ -180,6 +233,9 @@ def convert_documents(
    results: Iterator[ConversionResult] = converter.convert_all(
        sources,
        headers=headers,
+        page_range=options.page_range,
+        max_file_size=docling_serve_settings.max_file_size,
+        max_num_pages=docling_serve_settings.max_num_pages,
    )

    return results
--- a/docling_serve/gradio_ui.py
+++ b/docling_serve/gradio_ui.py
@@ -1,11 +1,22 @@
+import base64
 import importlib
 import json
 import logging
+import ssl
 import tempfile
+import time
 from pathlib import Path

+import certifi
 import gradio as gr
-import requests
+import httpx
+
+from docling.datamodel.pipeline_options import (
+    PdfBackend,
+    PdfPipeline,
+    TableFormerMode,
+    TableStructureOptions,
+)

 from docling_serve.helper_functions import _to_list_of_strings
 from docling_serve.settings import docling_serve_settings, uvicorn_settings
@@ -17,7 +28,7 @@ logger = logging.getLogger(__name__)
 ############################

 logo_path = "https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"
-js_components_url = "https://unpkg.com/@docling/docling-components@0.0.3"
+js_components_url = "https://unpkg.com/@docling/docling-components@0.0.6"
 if (
    docling_serve_settings.static_path is not None
    and docling_serve_settings.static_path.is_dir()
@@ -109,8 +120,29 @@ file_output_path = None  # Will be set when a new file is generated
 #############


+def get_api_endpoint() -> str:
+    protocol = "http"
+    if uvicorn_settings.ssl_keyfile is not None:
+        protocol = "https"
+    return f"{protocol}://{docling_serve_settings.api_host}:{uvicorn_settings.port}"
+
+
+def get_ssl_context() -> ssl.SSLContext:
+    ctx = ssl.create_default_context(cafile=certifi.where())
+    kube_sa_ca_cert_path = Path(
+        "/run/secrets/kubernetes.io/serviceaccount/service-ca.crt"
+    )
+    if (
+        uvicorn_settings.ssl_keyfile is not None
+        and ".svc." in docling_serve_settings.api_host
+        and kube_sa_ca_cert_path.exists()
+    ):
+        ctx.load_verify_locations(cafile=kube_sa_ca_cert_path)
+    return ctx
+
+
 def health_check():
-    response = requests.get(f"http://localhost:{uvicorn_settings.port}/health")
+    response = httpx.get(f"{get_api_endpoint()}/health")
    if response.status_code == 200:
        return "Healthy"
    return "Unhealthy"
@@ -126,6 +158,11 @@ def set_outputs_visibility_direct(x, y):
    return content, file


+def set_task_id_visibility(x):
+    task_id_row = gr.Row(visible=x)
+    return task_id_row
+
+
 def set_outputs_visibility_process(x):
    content = gr.Row(visible=not x)
    file = gr.Row(visible=x)
@@ -137,6 +174,7 @@ def set_download_button_label(label_text: gr.State):


 def clear_outputs():
+    task_id_rendered = ""
    markdown_content = ""
    json_content = ""
    json_rendered_content = ""
@@ -145,6 +183,7 @@ def clear_outputs():
    doctags_content = ""

    return (
+        task_id_rendered,
        markdown_content,
        markdown_content,
        json_content,
@@ -187,10 +226,56 @@ def change_ocr_lang(ocr_engine):
        return "english,chinese"


+def wait_task_finish(task_id: str, return_as_file: bool):
+    conversion_sucess = False
+    task_finished = False
+    task_status = ""
+    ssl_ctx = get_ssl_context()
+    while not task_finished:
+        try:
+            response = httpx.get(
+                f"{get_api_endpoint()}/v1alpha/status/poll/{task_id}?wait=5",
+                verify=ssl_ctx,
+                timeout=15,
+            )
+            task_status = response.json()["task_status"]
+            if task_status == "success":
+                conversion_sucess = True
+                task_finished = True
+
+            if task_status in ("failure", "revoked"):
+                conversion_sucess = False
+                task_finished = True
+                raise RuntimeError(f"Task failed with status {task_status!r}")
+            time.sleep(5)
+        except Exception as e:
+            logger.error(f"Error processing file(s): {e}")
+            conversion_sucess = False
+            task_finished = True
+            raise gr.Error(f"Error processing file(s): {e}", print_exception=False)
+
+    if conversion_sucess:
+        try:
+            response = httpx.get(
+                f"{get_api_endpoint()}/v1alpha/result/{task_id}",
+                timeout=15,
+                verify=ssl_ctx,
+            )
+            output = response_to_output(response, return_as_file)
+            return output
+        except Exception as e:
+            logger.error(f"Error getting task result: {e}")
+
+    raise gr.Error(
+        f"Error getting task result, conversion finished with status: {task_status}"
+    )
+
+
 def process_url(
    input_sources,
    to_formats,
    image_export_mode,
+    pipeline,
    ocr,
    force_ocr,
    ocr_engine,
@@ -209,6 +294,7 @@ def process_url(
        "options": {
            "to_formats": to_formats,
            "image_export_mode": image_export_mode,
+            "pipeline": pipeline,
            "ocr": ocr,
            "force_ocr": force_ocr,
            "ocr_engine": ocr_engine,
@@ -231,9 +317,12 @@ def process_url(
        logger.error("No input sources provided.")
        raise gr.Error("No input sources provided.", print_exception=False)
    try:
-        response = requests.post(
-            f"http://localhost:{uvicorn_settings.port}/v1alpha/convert/source",
+        ssl_ctx = get_ssl_context()
+        response = httpx.post(
+            f"{get_api_endpoint()}/v1alpha/convert/source/async",
            json=parameters,
+            verify=ssl_ctx,
+            timeout=60,
        )
    except Exception as e:
        logger.error(f"Error processing URL: {e}")
@@ -243,14 +332,22 @@ def process_url(
        error_message = data.get("detail", "An unknown error occurred.")
        logger.error(f"Error processing file: {error_message}")
        raise gr.Error(f"Error processing file: {error_message}", print_exception=False)
-    output = response_to_output(response, return_as_file)
-    return output
+
+    task_id_rendered = response.json()["task_id"]
+    return task_id_rendered
+
+
+def file_to_base64(file):
+    with open(file.name, "rb") as f:
+        encoded_string = base64.b64encode(f.read()).decode("utf-8")
+    return encoded_string


 def process_file(
-    files,
+    file,
    to_formats,
    image_export_mode,
+    pipeline,
    ocr,
    force_ocr,
    ocr_engine,
@@ -264,33 +361,39 @@ def process_file(
    do_picture_classification,
    do_picture_description,
 ):
-    if not files or len(files) == 0 or files[0] == "":
+    if not file or file == "":
        logger.error("No files provided.")
        raise gr.Error("No files provided.", print_exception=False)
-    files_data = [("files", (file.name, open(file.name, "rb"))) for file in files]
+    files_data = [{"base64_string": file_to_base64(file), "filename": file.name}]

    parameters = {
-        "to_formats": to_formats,
-        "image_export_mode": image_export_mode,
-        "ocr": str(ocr).lower(),
-        "force_ocr": str(force_ocr).lower(),
-        "ocr_engine": ocr_engine,
-        "ocr_lang": _to_list_of_strings(ocr_lang),
-        "pdf_backend": pdf_backend,
-        "table_mode": table_mode,
-        "abort_on_error": str(abort_on_error).lower(),
-        "return_as_file": str(return_as_file).lower(),
-        "do_code_enrichment": str(do_code_enrichment).lower(),
-        "do_formula_enrichment": str(do_formula_enrichment).lower(),
-        "do_picture_classification": str(do_picture_classification).lower(),
-        "do_picture_description": str(do_picture_description).lower(),
+        "file_sources": files_data,
+        "options": {
+            "to_formats": to_formats,
+            "image_export_mode": image_export_mode,
+            "pipeline": pipeline,
+            "ocr": ocr,
+            "force_ocr": force_ocr,
+            "ocr_engine": ocr_engine,
+            "ocr_lang": _to_list_of_strings(ocr_lang),
+            "pdf_backend": pdf_backend,
+            "table_mode": table_mode,
+            "abort_on_error": abort_on_error,
+            "return_as_file": return_as_file,
+            "do_code_enrichment": do_code_enrichment,
+            "do_formula_enrichment": do_formula_enrichment,
+            "do_picture_classification": do_picture_classification,
+            "do_picture_description": do_picture_description,
+        },
    }

    try:
-        response = requests.post(
-            f"http://localhost:{uvicorn_settings.port}/v1alpha/convert/file",
-            files=files_data,
-            data=parameters,
+        ssl_ctx = get_ssl_context()
+        response = httpx.post(
+            f"{get_api_endpoint()}/v1alpha/convert/source/async",
+            json=parameters,
+            verify=ssl_ctx,
+            timeout=60,
        )
    except Exception as e:
        logger.error(f"Error processing file(s): {e}")
@@ -300,8 +403,9 @@ def process_file(
        error_message = data.get("detail", "An unknown error occurred.")
        logger.error(f"Error processing file: {error_message}")
        raise gr.Error(f"Error processing file: {error_message}", print_exception=False)
-    output = response_to_output(response, return_as_file)
-    return output
+
+    task_id_rendered = response.json()["task_id"]
+    return task_id_rendered


 def response_to_output(response, return_as_file):
@@ -415,30 +519,31 @@ with gr.Blocks(
            )

    # URL Processing Tab
-    with gr.Tab("Convert URL(s)"):
+    with gr.Tab("Convert URL"):
        with gr.Row():
            with gr.Column(scale=4):
                url_input = gr.Textbox(
-                    label="Input Sources (comma-separated URLs)",
-                    placeholder="https://arxiv.org/pdf/2206.01062",
+                    label="URL Input Source",
+                    placeholder="https://arxiv.org/pdf/2501.17887",
                )
            with gr.Column(scale=1):
-                url_process_btn = gr.Button("Process URL(s)", scale=1)
+                url_process_btn = gr.Button("Process URL", scale=1)
                url_reset_btn = gr.Button("Reset", scale=1)

    # File Processing Tab
-    with gr.Tab("Convert File(s)"):
+    with gr.Tab("Convert File"):
        with gr.Row():
            with gr.Column(scale=4):
                file_input = gr.File(
                    elem_id="file_input_zone",
-                    label="Upload Files",
+                    label="Upload File",
                    file_types=[
                        ".pdf",
                        ".docx",
                        ".pptx",
                        ".html",
                        ".xlsx",
+                        ".json",
                        ".asciidoc",
                        ".txt",
                        ".md",
@@ -447,11 +552,11 @@ with gr.Blocks(
                        ".png",
                        ".gif",
                    ],
-                    file_count="multiple",
+                    file_count="single",
                    scale=4,
                )
            with gr.Column(scale=1):
-                file_process_btn = gr.Button("Process File(s)", scale=1)
+                file_process_btn = gr.Button("Process File", scale=1)
                file_reset_btn = gr.Button("Reset", scale=1)

    # Options
@@ -460,14 +565,14 @@ with gr.Blocks(
            with gr.Column(scale=1):
                to_formats = gr.CheckboxGroup(
                    [
-                        ("Markdown", "md"),
                        ("Docling (JSON)", "json"),
+                        ("Markdown", "md"),
                        ("HTML", "html"),
                        ("Plain Text", "text"),
                        ("Doc Tags", "doctags"),
                    ],
                    label="To Formats",
-                    value=["md"],
+                    value=["json", "md"],
                )
            with gr.Column(scale=1):
                image_export_mode = gr.Radio(
@@ -479,6 +584,13 @@ with gr.Blocks(
                    label="Image Export Mode",
                    value="embedded",
                )
+        with gr.Row():
+            with gr.Column(scale=1, min_width=200):
+                pipeline = gr.Radio(
+                    [(v.value.capitalize(), v.value) for v in PdfPipeline],
+                    label="Pipeline type",
+                    value=PdfPipeline.STANDARD.value,
+                )
        with gr.Row():
            with gr.Column(scale=1, min_width=200):
                ocr = gr.Checkbox(label="Enable OCR", value=True)
@@ -499,19 +611,23 @@ with gr.Blocks(
                )
            ocr_engine.change(change_ocr_lang, inputs=[ocr_engine], outputs=[ocr_lang])
        with gr.Row():
-            with gr.Column(scale=2):
+            with gr.Column(scale=4):
                pdf_backend = gr.Radio(
-                    ["pypdfium2", "dlparse_v1", "dlparse_v2"],
+                    [v.value for v in PdfBackend],
                    label="PDF Backend",
-                    value="dlparse_v2",
+                    value=PdfBackend.DLPARSE_V4.value,
                )
            with gr.Column(scale=2):
                table_mode = gr.Radio(
-                    ["fast", "accurate"], label="Table Mode", value="fast"
+                    [(v.value.capitalize(), v.value) for v in TableFormerMode],
+                    label="Table Mode",
+                    value=TableStructureOptions().mode.value,
                )
            with gr.Column(scale=1):
                abort_on_error = gr.Checkbox(label="Abort on Error", value=False)
-                return_as_file = gr.Checkbox(label="Return as File", value=False)
+                return_as_file = gr.Checkbox(
+                    label="Return as File", visible=False, value=False
+                )  # Disable until async handle output as file
        with gr.Row():
            with gr.Column():
                do_code_enrichment = gr.Checkbox(
@@ -528,18 +644,22 @@ with gr.Blocks(
                    label="Enable picture description", value=False
                )

+    # Task id output
+    with gr.Row(visible=False) as task_id_output:
+        task_id_rendered = gr.Textbox(label="Task id", interactive=False)
+
    # Document output
    with gr.Row(visible=False) as content_output:
+        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(label="Response")
        with gr.Tab("Markdown"):
            output_markdown = gr.Code(
                language="markdown", wrap_lines=True, show_label=False
            )
        with gr.Tab("Markdown-Rendered"):
            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"):
@@ -557,36 +677,34 @@ with gr.Blocks(
    # UI Actions #
    ##############

+    # Disable until async handle output as file
    # Handle Return as File
-    url_input.change(
-        auto_set_return_as_file,
-        inputs=[url_input, file_input, image_export_mode],
-        outputs=[return_as_file],
-    )
-    file_input.change(
-        auto_set_return_as_file,
-        inputs=[url_input, file_input, image_export_mode],
-        outputs=[return_as_file],
-    )
-    image_export_mode.change(
-        auto_set_return_as_file,
-        inputs=[url_input, file_input, image_export_mode],
-        outputs=[return_as_file],
-    )
+    # url_input.change(
+    #     auto_set_return_as_file,
+    #     inputs=[url_input, file_input, image_export_mode],
+    #     outputs=[return_as_file],
+    # )
+    # file_input.change(
+    #     auto_set_return_as_file,
+    #     inputs=[url_input, file_input, image_export_mode],
+    #     outputs=[return_as_file],
+    # )
+    # image_export_mode.change(
+    #     auto_set_return_as_file,
+    #     inputs=[url_input, file_input, image_export_mode],
+    #     outputs=[return_as_file],
+    # )

    # URL processing
    url_process_btn.click(
        set_options_visibility, inputs=[false_bool], outputs=[options]
    ).then(
        set_download_button_label, inputs=[processing_text], outputs=[download_file_btn]
-    ).then(
-        set_outputs_visibility_process,
-        inputs=[return_as_file],
-        outputs=[content_output, file_output],
    ).then(
        clear_outputs,
        inputs=None,
        outputs=[
+            task_id_rendered,
            output_markdown,
            output_markdown_rendered,
            output_json,
@@ -596,12 +714,17 @@ with gr.Blocks(
            output_text,
            output_doctags,
        ],
+    ).then(
+        set_task_id_visibility,
+        inputs=[true_bool],
+        outputs=[task_id_output],
    ).then(
        process_url,
        inputs=[
            url_input,
            to_formats,
            image_export_mode,
+            pipeline,
            ocr,
            force_ocr,
            ocr_engine,
@@ -615,6 +738,16 @@ with gr.Blocks(
            do_picture_classification,
            do_picture_description,
        ],
+        outputs=[
+            task_id_rendered,
+        ],
+    ).then(
+        set_outputs_visibility_process,
+        inputs=[return_as_file],
+        outputs=[content_output, file_output],
+    ).then(
+        wait_task_finish,
+        inputs=[task_id_rendered, return_as_file],
        outputs=[
            output_markdown,
            output_markdown_rendered,
@@ -645,21 +778,20 @@ with gr.Blocks(
        set_outputs_visibility_direct,
        inputs=[false_bool, false_bool],
        outputs=[content_output, file_output],
-    ).then(clear_url_input, inputs=None, outputs=[url_input])
+    ).then(set_task_id_visibility, inputs=[false_bool], outputs=[task_id_output]).then(
+        clear_url_input, inputs=None, outputs=[url_input]
+    )

    # File processing
    file_process_btn.click(
        set_options_visibility, inputs=[false_bool], outputs=[options]
    ).then(
        set_download_button_label, inputs=[processing_text], outputs=[download_file_btn]
-    ).then(
-        set_outputs_visibility_process,
-        inputs=[return_as_file],
-        outputs=[content_output, file_output],
    ).then(
        clear_outputs,
        inputs=None,
        outputs=[
+            task_id_rendered,
            output_markdown,
            output_markdown_rendered,
            output_json,
@@ -669,12 +801,17 @@ with gr.Blocks(
            output_text,
            output_doctags,
        ],
+    ).then(
+        set_task_id_visibility,
+        inputs=[true_bool],
+        outputs=[task_id_output],
    ).then(
        process_file,
        inputs=[
            file_input,
            to_formats,
            image_export_mode,
+            pipeline,
            ocr,
            force_ocr,
            ocr_engine,
@@ -688,6 +825,16 @@ with gr.Blocks(
            do_picture_classification,
            do_picture_description,
        ],
+        outputs=[
+            task_id_rendered,
+        ],
+    ).then(
+        set_outputs_visibility_process,
+        inputs=[return_as_file],
+        outputs=[content_output, file_output],
+    ).then(
+        wait_task_finish,
+        inputs=[task_id_rendered, return_as_file],
        outputs=[
            output_markdown,
            output_markdown_rendered,
@@ -718,4 +865,6 @@ with gr.Blocks(
        set_outputs_visibility_direct,
        inputs=[false_bool, false_bool],
        outputs=[content_output, file_output],
-    ).then(clear_file_input, inputs=None, outputs=[file_input])
+    ).then(set_task_id_visibility, inputs=[false_bool], outputs=[task_id_output]).then(
+        clear_file_input, inputs=None, outputs=[file_input]
+    )
--- a/docling_serve/settings.py
+++ b/docling_serve/settings.py
@@ -1,3 +1,4 @@
+import sys
 from pathlib import Path
 from typing import Optional, Union

@@ -32,11 +33,16 @@ class DoclingServeSettings(BaseSettings):
    )

    enable_ui: bool = False
+    api_host: str = "localhost"
    artifacts_path: Optional[Path] = None
    static_path: Optional[Path] = None
    options_cache_size: int = 2
    allow_external_plugins: bool = False

+    max_document_timeout: float = 3_600 * 24 * 7  # 7 days
+    max_num_pages: int = sys.maxsize
+    max_file_size: int = sys.maxsize
+
    cors_origins: list[str] = ["*"]
    cors_methods: list[str] = ["*"]
    cors_headers: list[str] = ["*"]
--- a/docs/deploy-examples/compose-gpu.yaml
+++ b/docs/deploy-examples/compose-gpu.yaml
@@ -0,0 +1,15 @@
+services:
+  docling:
+    image: ghcr.io/docling-project/docling-serve-cu124
+    container_name: docling-serve
+    ports:
+      - 5001:5001
+    environment:
+      - DOCLING_SERVE_ENABLE_UI=true
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: all # nvidia-smi 
+            capabilities: [gpu]
--- a/docs/deploy-examples/docling-serve-oauth.yaml
+++ b/docs/deploy-examples/docling-serve-oauth.yaml
@@ -9,41 +9,18 @@ metadata:
  annotations:
    serviceaccounts.openshift.io/oauth-redirectreference.primary: '{"kind":"OAuthRedirectReference","apiVersion":"v1","reference":{"kind":"Route","name":"docling-serve"}}'
 ---
-kind: Role
 apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
 metadata:
  name: docling-serve-oauth
-  labels:
-    app: docling-serve
-    component: docling-serve-api
-rules:
-  - verbs:
-      - create
-    apiGroups:
-      - authorization.k8s.io
-    resources:
-      - subjectaccessreviews
-  - verbs:
-      - create
-    apiGroups:
-      - authentication.k8s.io
-    resources:
-      - tokenreviews
---
-kind: RoleBinding
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: docling-serve-oauth
-  labels:
-    app: docling-serve
-    component: docling-serve-api
-subjects:
-  - kind: ServiceAccount
-    name: docling-serve
 roleRef:
  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: docling-serve-oauth
+  kind: ClusterRole
+  name: system:auth-delegator
+subjects:
+- kind: ServiceAccount
+  name: docling-serve
+  namespace: docling
 ---
 apiVersion: route.openshift.io/v1
 kind: Route
@@ -107,10 +84,10 @@ spec:
        - name: api
          resources:
            limits:
-              cpu: 500m
+              cpu: 2000m
              memory: 2Gi
            requests:
-              cpu: 250m
+              cpu: 800m
              memory: 1Gi
          readinessProbe:
            httpGet:
@@ -128,13 +105,19 @@ spec:
              port: http
              scheme: HTTPS
            initialDelaySeconds: 3
-            timeoutSeconds: 2
-            periodSeconds: 5
+            timeoutSeconds: 4
+            periodSeconds: 10
            successThreshold: 1
-            failureThreshold: 3
+            failureThreshold: 5
          env:
+            - name: NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
            - name: DOCLING_SERVE_ENABLE_UI
              value: 'true'
+            - name: DOCLING_SERVE_API_HOST
+              value: 'docling-serve.$(NAMESPACE).svc.cluster.local'
            - name: UVICORN_SSL_CERTFILE
              value: '/etc/tls/private/tls.crt'
            - name: UVICORN_SSL_KEYFILE
@@ -147,7 +130,7 @@ spec:
            - name: proxy-tls
              mountPath: /etc/tls/private
          imagePullPolicy: Always
-          image: 'ghcr.io/docling-project/docling-serve:dev-ssl'
+          image: 'ghcr.io/docling-project/docling-serve-cpu:fix-ui-with-https'
        - name: oauth-proxy
          resources:
            limits:
--- a/docs/deploy-examples/docling-serve-simple.yaml
+++ b/docs/deploy-examples/docling-serve-simple.yaml
@@ -0,0 +1,58 @@
+# This example deployment configures Docling Serve with a Service and cuda image
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: docling-serve
+  labels:
+    app: docling-serve
+    component: docling-serve-api
+spec:
+  ports:
+  - name: http
+    port: 5001
+    targetPort: http
+  selector:
+    app: docling-serve
+    component: docling-serve-api
+---
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  name: docling-serve
+  labels:
+    app: docling-serve
+    component: docling-serve-api
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: docling-serve
+      component: docling-serve-api
+  template:
+    metadata:
+      labels:
+        app: docling-serve
+        component: docling-serve-api
+    spec:
+      restartPolicy: Always
+      containers:
+        - name: api
+          resources:
+            limits:
+              cpu: 500m
+              memory: 2Gi
+              nvidia.com/gpu: 1  # Limit to one GPU
+            requests:
+              cpu: 250m
+              memory: 1Gi
+              nvidia.com/gpu: 1  # Limit to one GPU
+          env:
+            - name: DOCLING_SERVE_ENABLE_UI
+              value: 'true'
+          ports:
+            - name: http
+              containerPort: 5001
+              protocol: TCP
+          imagePullPolicy: Always
+          image: 'ghcr.io/docling-project/docling-serve-cu124'
--- a/docs/deployment.md
+++ b/docs/deployment.md
@@ -1,7 +1,161 @@
-# Deployment
+# Deployment Examples
+
+This document provides deployment examples for running the application in different environments.
+
+Choose the deployment option that best fits your setup.
+
+- **[Local GPU](#local-gpu)**: For deploying the application locally on a machine with a NVIDIA GPU (using Docker Compose).
+- **[OpenShift](#openshift)**: For deploying the application on an OpenShift cluster, designed for cloud-native environments.
+
+---
+
+## Local GPU
+
+### Docker compose
+
+Manifest example: [compose-gpu.yaml](./deploy-examples/compose-gpu.yaml)
+
+This deployment has the following features:
+
+- NVIDIA cuda enabled
+
+Install the app with:
+
+```sh
+docker compose -f docs/deploy-examples/compose-gpu.yaml up -d
+```
+
+For using the API:
+
+```sh
+# Make a test query
+curl -X 'POST' \
+  "localhost:5001/v1alpha/convert/source/async" \
+  -H "accept: application/json" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}]
+  }'
+```
+
+<details>
+<summary><b>Requirements</b></summary>
+
+- debian/ubuntu/rhel/fedora/opensuse
+- docker
+- nvidia drivers >=550.54.14
+- nvidia-container-toolkit
+
+Docs:
+
+- [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/supported-platforms.html)
+- [CUDA Toolkit Release Notes](https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html#id6)
+
+</details>
+
+<details>
+<summary><b>Steps</b></summary>
+
+1. Check driver version and which GPU you want to use (0/1/2/3.. and update [compose-gpu.yaml](./deploy-examples/compose-gpu.yaml) file or use `count: all`)
+
+    ```sh
+    nvidia-smi
+    ```
+
+2. Check if the NVIDIA Container Toolkit is installed/updated
+
+    ```sh
+    # debian
+    dpkg -l | grep nvidia-container-toolkit
+    ```
+
+    ```sh
+    # rhel
+    rpm -q nvidia-container-toolkit
+    ```
+
+    NVIDIA Container Toolkit install steps can be found here:
+
+    <https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html>
+
+3. Check which runtime is being used by Docker
+
+    ```sh
+    # docker
+    docker info | grep -i runtime
+    ```
+
+4. If the default Docker runtime changes back from 'nvidia' to 'default' after restarting the Docker service (optional):
+
+    Backup the daemon.json file:
+
+    ```sh
+    sudo cp /etc/docker/daemon.json /etc/docker/daemon.json.bak
+    ```
+
+    Update the daemon.json file:
+
+    ```sh
+    echo '{
+      "runtimes": {
+        "nvidia": {
+          "path": "nvidia-container-runtime"
+        }
+      },
+      "default-runtime": "nvidia"
+    }' | sudo tee /etc/docker/daemon.json > /dev/null
+    ```
+
+    Restart the Docker service:
+
+    ```sh
+    sudo systemctl restart docker
+    ```
+
+    Confirm 'nvidia' is the default runtime used by Docker by repeating step 3.
+
+5. Run the container:
+
+    ```sh
+    docker compose -f docs/deploy-examples/compose-gpu.yaml up -d
+    ```
+
+</details>

 ## OpenShift

+### Simple deployment
+
+Manifest example: [docling-serve-simple.yaml](./deploy-examples/docling-serve-simple.yaml)
+
+This deployment example has the following features:
+
+- Deployment configuration
+- Service configuration
+- NVIDIA cuda enabled
+
+Install the app with:
+
+```sh
+oc apply -f docs/deploy-examples/docling-serve-simple.yaml
+```
+
+For using the API:
+
+```sh
+# Port-forward the service
+oc port-forward svc/docling-serve 5001:5001
+
+# Make a test query
+curl -X 'POST' \
+  "localhost:5001/v1alpha/convert/source/async" \
+  -H "accept: application/json" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}]
+  }'
+```
+
 ### Secure deployment with `oauth-proxy`

 Manifest example: [docling-serve-oauth.yaml](./deploy-examples/docling-serve-oauth.yaml)
@@ -15,7 +169,7 @@ This deployment has the following features:
 Install the app with:

 ```sh
-kubectl apply -f docs/deploy-examples/docling-serve-oauth.yaml
+oc apply -f docs/deploy-examples/docling-serve-oauth.yaml
 ```

 For using the API:
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.7.0"  # DO NOT EDIT, updated automatically
+version = "0.8.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [
@@ -30,7 +30,8 @@ classifiers = [
 ]
 requires-python = ">=3.10"
 dependencies = [
-    "docling~=2.28",
+    "docling[vlm]~=2.28",
+    "mlx-vlm~=0.1.12; sys_platform == 'darwin' and platform_machine == 'arm64'",
    "fastapi[standard]~=0.115",
    "httpx~=0.28",
    "pydantic~=2.10",
@@ -43,7 +44,8 @@ dependencies = [

 [project.optional-dependencies]
 ui = [
-    "gradio~=5.9"
+    "gradio~=5.9",
+    "pydantic<2.11.0",  # fix compatibility between gradio and new pydantic 2.11
 ]
 tesserocr = [
    "tesserocr~=2.7"
@@ -195,6 +197,7 @@ module = [
    "tesserocr.*",
    "rapidocr_onnxruntime.*",
    "requests.*",
+    "mlx_vlm.*",
 ]
 ignore_missing_imports = true

--- a/tests/test_1-file-all-outputs.py
+++ b/tests/test_1-file-all-outputs.py
@@ -92,16 +92,11 @@ async def test_convert_file(async_client):
            msg=f'JSON document should contain \'{{\\n  "schema_name": "DoclingDocument\'". Received: {safe_slice(data["document"]["json_content"])}',
        )
    # HTML check
-    check.is_in(
-        "html_content",
-        data.get("document", {}),
-        msg=f"Response should contain 'html_content' key. Received keys: {list(data.get('document', {}).keys())}",
-    )
    if data.get("document", {}).get("html_content") is not None:
        check.is_in(
-            '<!DOCTYPE html>\n<html lang="en">\n<head>',
+            "<!DOCTYPE html>\n<html>\n<head>",
            data["document"]["html_content"],
-            msg=f"HTML document should contain '<!DOCTYPE html>\\n<html lang=\"en'>. Received: {safe_slice(data['document']['html_content'])}",
+            msg=f"HTML document should contain '<!DOCTYPE html>\\n<html>'. Received: {safe_slice(data['document']['html_content'])}",
        )
    # Text check
    check.is_in(
@@ -123,7 +118,7 @@ async def test_convert_file(async_client):
    )
    if data.get("document", {}).get("doctags_content") is not None:
        check.is_in(
-            "<document>\n<section_header_level_1><location>",
+            "<doctag><page_header><loc",
            data["document"]["doctags_content"],
-            msg=f"DocTags document should contain '<document>\\n<section_header_level_1><location>'. Received: {safe_slice(data['document']['doctags_content'])}",
+            msg=f"DocTags document should contain '<doctag><page_header><loc'. Received: {safe_slice(data['document']['doctags_content'])}",
        )
--- a/tests/test_1-url-all-outputs.py
+++ b/tests/test_1-url-all-outputs.py
@@ -93,9 +93,9 @@ async def test_convert_url(async_client):
    )
    if data.get("document", {}).get("html_content") is not None:
        check.is_in(
-            '<!DOCTYPE html>\n<html lang="en">\n<head>',
+            "<!DOCTYPE html>\n<html>\n<head>",
            data["document"]["html_content"],
-            msg=f"HTML document should contain '<!DOCTYPE html>\\n<html lang=\"en'>. Received: {safe_slice(data['document']['html_content'])}",
+            msg=f"HTML document should contain '<!DOCTYPE html>\\n<html>'. Received: {safe_slice(data['document']['html_content'])}",
        )
    # Text check
    check.is_in(
@@ -117,7 +117,7 @@ async def test_convert_url(async_client):
    )
    if data.get("document", {}).get("doctags_content") is not None:
        check.is_in(
-            "<document>\n<section_header_level_1><location>",
+            "<doctag><page_header><loc",
            data["document"]["doctags_content"],
-            msg=f"DocTags document should contain '<document>\\n<section_header_level_1><location>'. Received: {safe_slice(data['document']['doctags_content'])}",
+            msg=f"DocTags document should contain '<doctag><page_header><loc'. Received: {safe_slice(data['document']['doctags_content'])}",
        )
--- a/uv.lock
+++ b/uv.lock
Author	SHA1	Message	Date
github-actions[bot]	40bb21d347	chore: bump version to 0.8.0 [skip ci]	2025-04-22 13:04:33 +00:00
Michele Dolfi	ee89ee4dae	feat: Add option for vlm pipeline (#143 ) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-22 14:46:33 +02:00
Michele Dolfi	6b3d281f02	feat: Expose more conversion options (#142 ) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-22 10:41:47 +02:00
Tiago Santana	b598872e5c	feat(UI): change UI to use async endpoints (#131 ) Signed-off-by: Tiago Santana <54704492+SantanaTiago@users.noreply.github.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-19 19:59:07 +02:00
Michele Dolfi	087417e5c2	docs: fix required permissions for oauth2-proxy requests (#141 ) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-19 18:46:28 +02:00
Michele Dolfi	57f9073bc0	fix(UI): use https when calling the api (#139 ) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-19 17:35:54 +02:00
Rui Dias Gomes	525a43ff6f	docs: update deployment examples (#135 ) Signed-off-by: rmdg88 <rmdg88@gmail.com> Signed-off-by: Rui Dias Gomes <66125272+rmdg88@users.noreply.github.com>	2025-04-17 14:29:34 +02:00
Michele Dolfi	c1ce4719c9	fix: fix permissions in docker image (#136 ) Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>	2025-04-17 14:27:43 +02:00
Kasper Dinkla	5dfb75d3b9	fix: picture caption visuals (#129 ) Signed-off-by: DKL <dkl@zurich.ibm.com>	2025-04-15 13:17:00 +02:00
Michele Dolfi	420162e674	docs: fix image tag (#124 ) Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>	2025-04-11 16:19:39 +02:00