chore: bump version to 1.9.0 [skip ci]

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

.github/styles/config/vocabularies/Docling/accept.txt

@@ -4,6 +4,7 @@ asgi
 async
 (?i)urls
 uvicorn
+Config
 [Ww]ebserver
 RQ
 (?i)url

.github/workflows/job-image.yml

@@ -160,13 +160,10 @@ jobs:
               pip install uv
               uv venv --allow-existing
               source .venv/bin/activate
-              uv sync --all-extras --no-extra flash-attn
+              uv sync --only-dev
 
               # Run pytest tests
               echo "Running tests..."
-              # Test import
-              python -c 'from docling_serve.app import create_app; create_app()'
-
               # Run pytest and check result directly
               if ! pytest -sv -k "test_convert_url" tests/test_1-url-async.py \
                 --disable-warnings; then

CHANGELOG.md

@@ -1,3 +1,42 @@
+## [v1.9.0](https://github.com/docling-project/docling-serve/releases/tag/v1.9.0) - 2025-11-24
+
+### Feature
+
+* Version endpoint ([#442](https://github.com/docling-project/docling-serve/issues/442)) ([`2c23f65`](https://github.com/docling-project/docling-serve/commit/2c23f65507d7699694debd7faa0de840ef2d2cb7))
+
+### Fix
+
+* Dependencies updates – Docling 2.63.0 ([#443](https://github.com/docling-project/docling-serve/issues/443)) ([`e437e83`](https://github.com/docling-project/docling-serve/commit/e437e830c956f9a76cd0c62faf9add0231992548))
+
+### Docling libraries included in this release:
+- docling 2.63.0
+- docling-core 2.52.0
+- docling-ibm-models 3.10.2
+- docling-jobkit 1.8.0
+- docling-mcp 1.3.3
+- docling-parse 4.7.1
+- docling-serve 1.9.0
+
+## [v1.8.0](https://github.com/docling-project/docling-serve/releases/tag/v1.8.0) - 2025-10-31
+
+### Feature
+
+* Docling with new standard pipeline with threading ([#428](https://github.com/docling-project/docling-serve/issues/428)) ([`bf132a3`](https://github.com/docling-project/docling-serve/commit/bf132a3c3e615ddbe624841ea5b3a98593c00654))
+
+### Documentation
+
+* Expand automatic docs to nested objects. More complete usage docs. ([#426](https://github.com/docling-project/docling-serve/issues/426)) ([`35319b0`](https://github.com/docling-project/docling-serve/commit/35319b0da793a2a1a434fd2b60b7632e10ecced3))
+* Add docs for docling parameters like performance and debug ([#424](https://github.com/docling-project/docling-serve/issues/424)) ([`f3957ae`](https://github.com/docling-project/docling-serve/commit/f3957aeb577097121fe9d0d21f75a50643f03369))
+
+### Docling libraries included in this release:
+- docling 2.60.0
+- docling-core 2.50.0
+- docling-ibm-models 3.10.2
+- docling-jobkit 1.8.0
+- docling-mcp 1.3.2
+- docling-parse 4.7.0
+- docling-serve 1.8.0
+
 ## [v1.7.2](https://github.com/docling-project/docling-serve/releases/tag/v1.7.2) - 2025-10-30
 
 ### Fix

docling_serve/__main__.py

@@ -30,7 +30,7 @@ logger = logging.getLogger(__name__)
 
 def version_callback(value: bool) -> None:
     if value:
-        docling_serve_version = importlib.metadata.version("docling_serve")
+        docling_serve_version = importlib.metadata.version("docling-serve")
         docling_jobkit_version = importlib.metadata.version("docling-jobkit")
         docling_version = importlib.metadata.version("docling")
         docling_core_version = importlib.metadata.version("docling-core")
@@ -385,6 +385,11 @@ def rq_worker() -> Any:
         allow_external_plugins=docling_serve_settings.allow_external_plugins,
         max_num_pages=docling_serve_settings.max_num_pages,
         max_file_size=docling_serve_settings.max_file_size,
+        queue_max_size=docling_serve_settings.queue_max_size,
+        ocr_batch_size=docling_serve_settings.ocr_batch_size,
+        layout_batch_size=docling_serve_settings.layout_batch_size,
+        table_batch_size=docling_serve_settings.table_batch_size,
+        batch_polling_interval_seconds=docling_serve_settings.batch_polling_interval_seconds,
     )
 
     run_worker(

docling_serve/app.py

@@ -76,7 +76,7 @@ from docling_serve.datamodel.responses import (
     TaskStatusResponse,
     WebsocketMessage,
 )
-from docling_serve.helper_functions import FormDepends
+from docling_serve.helper_functions import DOCLING_VERSIONS, FormDepends
 from docling_serve.orchestrator_factory import get_async_orchestrator
 from docling_serve.response_preparation import prepare_response
 from docling_serve.settings import docling_serve_settings
@@ -437,6 +437,16 @@ def create_app():  # noqa: C901
     def api_check() -> HealthCheckResponse:
         return HealthCheckResponse()
 
+    # Docling versions
+    @app.get("/version", tags=["health"])
+    def version_info() -> dict:
+        if not docling_serve_settings.show_version_info:
+            raise HTTPException(
+                status_code=status.HTTP_403_FORBIDDEN,
+                detail="Forbidden. The server is configured for not showing version details.",
+            )
+        return DOCLING_VERSIONS
+
     # Convert a document from URL(s)
     @app.post(
         "/v1/convert/source",

docling_serve/helper_functions.py

@@ -1,11 +1,25 @@
+import importlib.metadata
 import inspect
 import json
+import platform
 import re
+import sys
 from typing import Union, get_args, get_origin
 
 from fastapi import Depends, Form
 from pydantic import BaseModel, TypeAdapter
 
+DOCLING_VERSIONS = {
+    "docling-serve": importlib.metadata.version("docling-serve"),
+    "docling-jobkit": importlib.metadata.version("docling-jobkit"),
+    "docling": importlib.metadata.version("docling"),
+    "docling-core": importlib.metadata.version("docling-core"),
+    "docling-ibm-models": importlib.metadata.version("docling-ibm-models"),
+    "docling-parse": importlib.metadata.version("docling-parse"),
+    "python": f"{sys.implementation.cache_tag} ({platform.python_version()})",
+    "plaform": platform.platform(),
+}
+
 
 def is_pydantic_model(type_):
     try:

docling_serve/orchestrator_factory.py

@@ -288,6 +288,11 @@ def get_async_orchestrator() -> BaseOrchestrator:
             allow_external_plugins=docling_serve_settings.allow_external_plugins,
             max_num_pages=docling_serve_settings.max_num_pages,
             max_file_size=docling_serve_settings.max_file_size,
+            queue_max_size=docling_serve_settings.queue_max_size,
+            ocr_batch_size=docling_serve_settings.ocr_batch_size,
+            layout_batch_size=docling_serve_settings.layout_batch_size,
+            table_batch_size=docling_serve_settings.table_batch_size,
+            batch_polling_interval_seconds=docling_serve_settings.batch_polling_interval_seconds,
         )
         cm = DoclingConverterManager(config=cm_config)
 

docling_serve/settings.py

@@ -50,6 +50,7 @@ class DoclingServeSettings(BaseSettings):
     options_cache_size: int = 2
     enable_remote_services: bool = False
     allow_external_plugins: bool = False
+    show_version_info: bool = True
 
     api_key: str = ""
 
@@ -57,6 +58,13 @@ class DoclingServeSettings(BaseSettings):
     max_num_pages: int = sys.maxsize
     max_file_size: int = sys.maxsize
 
+    # Threading pipeline
+    queue_max_size: Optional[int] = None
+    ocr_batch_size: Optional[int] = None
+    layout_batch_size: Optional[int] = None
+    table_batch_size: Optional[int] = None
+    batch_polling_interval_seconds: Optional[float] = None
+
     sync_poll_interval: int = 2  # seconds
     max_sync_wait: int = 120  # 2 minutes
 

docs/configuration.md

@@ -39,24 +39,42 @@ THe following table describes the options to configure the Docling Serve app.
 |  | `DOCLING_SERVE_STATIC_PATH` | unset | If set to a valid directory, the static assets for the docs and UI will be loaded from this path |
 |  | `DOCLING_SERVE_SCRATCH_PATH` |  | If set, this directory will be used as scratch workspace, e.g. storing the results before they get requested. If unset, a temporary created is created for this purpose. |
 | `--enable-ui` | `DOCLING_SERVE_ENABLE_UI` | `false` | Enable the demonstrator UI. |
+|  | `DOCLING_SERVE_SHOW_VERSION_INFO` | `true` | If enabled, the `/version` endpoint will provide the Docling package versions, otherwise it will return a forbidden 403 error. |
 |  | `DOCLING_SERVE_ENABLE_REMOTE_SERVICES` | `false` | Allow pipeline components making remote connections. For example, this is needed when using a vision-language model via APIs. |
 |  | `DOCLING_SERVE_ALLOW_EXTERNAL_PLUGINS` | `false` | Allow the selection of third-party plugins. |
 |  | `DOCLING_SERVE_SINGLE_USE_RESULTS` | `true` | If true, results can be accessed only once. If false, the results accumulate in the scratch directory. |
 |  | `DOCLING_SERVE_RESULT_REMOVAL_DELAY` | `300` | When `DOCLING_SERVE_SINGLE_USE_RESULTS` is active, this is the delay before results are removed from the task registry. |
 |  | `DOCLING_SERVE_MAX_DOCUMENT_TIMEOUT` | `604800` (7 days) | The maximum time for processing a document. |
-|  | `DOCLING_NUM_THREADS` | `4` | Number of concurrent threads for processing a document. |
 |  | `DOCLING_SERVE_MAX_NUM_PAGES` |  | The maximum number of pages for a document to be processed. |
 |  | `DOCLING_SERVE_MAX_FILE_SIZE` |  | The maximum file size for a document to be processed. |
 |  | `DOCLING_SERVE_SYNC_POLL_INTERVAL` | `2` | Number of seconds to sleep between polling the task status in the sync endpoints. |
 |  | `DOCLING_SERVE_MAX_SYNC_WAIT` | `120` | Max number of seconds a synchronous endpoint is waiting for the task completion. |
 |  | `DOCLING_SERVE_LOAD_MODELS_AT_BOOT` | `True` | If enabled, the models for the default options will be loaded at boot. |
 |  | `DOCLING_SERVE_OPTIONS_CACHE_SIZE` | `2` | How many DocumentConveter objects (including their loaded models) to keep in the cache. |
+|  | `DOCLING_SERVE_QUEUE_MAX_SIZE` | | Size of the pages queue. Potentially so many pages opened at the same time. |
+|  | `DOCLING_SERVE_OCR_BATCH_SIZE` | | Batch size for the OCR stage. |
+|  | `DOCLING_SERVE_LAYOUT_BATCH_SIZE` | | Batch size for the layout detection stage. |
+|  | `DOCLING_SERVE_TABLE_BATCH_SIZE` | | Batch size for the table structure stage. |
+|  | `DOCLING_SERVE_BATCH_POLLING_INTERVAL_SECONDS` | | Wait time for gathering pages before starting a stage processing. |
 |  | `DOCLING_SERVE_CORS_ORIGINS` | `["*"]` | A list of origins that should be permitted to make cross-origin requests. |
 |  | `DOCLING_SERVE_CORS_METHODS` | `["*"]` | A list of HTTP methods that should be allowed for cross-origin requests. |
 |  | `DOCLING_SERVE_CORS_HEADERS` | `["*"]` | A list of HTTP request headers that should be supported for cross-origin requests. |
 |  | `DOCLING_SERVE_API_KEY` | | If specified, all the API requests must contain the header `X-Api-Key` with this value. |
 |  | `DOCLING_SERVE_ENG_KIND` | `local` | The compute engine to use for the async tasks. Possible values are `local`, `rq` and `kfp`. See below for more configurations of the engines. |
 
+### Docling configuration
+
+Some Docling settings, mostly about performance, are exposed as environment variable which can be used also when running Docling Serve.
+
+| ENV | Default | Description |
+| ----|---------|-------------|
+| `DOCLING_NUM_THREADS` | `4` | Number of concurrent threads used for the `torch` CPU execution. |
+| `DOCLING_DEVICE` | | Device used for the model execution. Valid values are `cpu`, `cuda`, `mps`. When unset, the best device is chosen. For CUDA-enabled environments, you can choose which GPU using the syntax `cuda:0`, `cuda:1`, ... |
+| `DOCLING_PERF_PAGE_BATCH_SIZE` | `4` | Number of pages processed in the same batch. |
+| `DOCLING_PERF_ELEMENTS_BATCH_SIZE` | `8` | Number of document items/elements processed in the same batch during enrichment. |
+| `DOCLING_DEBUG_PROFILE_PIPELINE_TIMINGS` | `false` | When enabled, Docling will provide detailed timings information. |
+
+
 ### Compute engine
 
 Docling Serve can be deployed with several possible of compute engine.

docs/usage.md

@@ -7,6 +7,7 @@ The API provides two endpoints: one for urls, one for files. This is necessary t
 On top of the source of file (see below), both endpoints support the same parameters.
 
 <!-- begin: parameters-docs -->
+<h4>ConvertDocumentsRequestOptions</h4>
 
 | Field Name | Type | Description |
 |------------|------|-------------|
@@ -39,6 +40,52 @@ On top of the source of file (see below), both endpoints support the same parame
 | `vlm_pipeline_model_local` | VlmModelLocal or NoneType | Options for running a local vision-language model for the `vlm` pipeline. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with `vlm_pipeline_model_api` and `vlm_pipeline_model`. |
 | `vlm_pipeline_model_api` | VlmModelApi or NoneType | API details for using a vision-language model for the `vlm` pipeline. This parameter is mutually exclusive with `vlm_pipeline_model_local` and `vlm_pipeline_model`. |
 
+<h4>VlmModelApi</h4>
+
+| Field Name | Type | Description |
+|------------|------|-------------|
+| `url` | AnyUrl | Endpoint which accepts openai-api compatible requests. |
+| `headers` | Dict[str, str] | Headers used for calling the API endpoint. For example, it could include authentication headers. |
+| `params` | Dict[str, Any] | Model parameters. |
+| `timeout` | float | Timeout for the API request. |
+| `concurrency` | int | Maximum number of concurrent requests to the API. |
+| `prompt` | str | Prompt used when calling the vision-language model. |
+| `scale` | float | Scale factor of the images used. |
+| `response_format` | ResponseFormat | Type of response generated by the model. |
+| `temperature` | float | Temperature parameter controlling the reproducibility of the result. |
+
+<h4>VlmModelLocal</h4>
+
+| Field Name | Type | Description |
+|------------|------|-------------|
+| `repo_id` | str | Repository id from the Hugging Face Hub. |
+| `prompt` | str | Prompt used when calling the vision-language model. |
+| `scale` | float | Scale factor of the images used. |
+| `response_format` | ResponseFormat | Type of response generated by the model. |
+| `inference_framework` | InferenceFramework | Inference framework to use. |
+| `transformers_model_type` | TransformersModelType | Type of transformers auto-model to use. |
+| `extra_generation_config` | Dict[str, Any] | Config from https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig |
+| `temperature` | float | Temperature parameter controlling the reproducibility of the result. |
+
+<h4>PictureDescriptionApi</h4>
+
+| Field Name | Type | Description |
+|------------|------|-------------|
+| `url` | AnyUrl | Endpoint which accepts openai-api compatible requests. |
+| `headers` | Dict[str, str] | Headers used for calling the API endpoint. For example, it could include authentication headers. |
+| `params` | Dict[str, Any] | Model parameters. |
+| `timeout` | float | Timeout for the API request. |
+| `concurrency` | int | Maximum number of concurrent requests to the API. |
+| `prompt` | str | Prompt used when calling the vision-language model. |
+
+<h4>PictureDescriptionLocal</h4>
+
+| Field Name | Type | Description |
+|------------|------|-------------|
+| `repo_id` | str | Repository id from the Hugging Face Hub. |
+| `prompt` | str | Prompt used when calling the vision-language model. |
+| `generation_config` | Dict[str, Any] | Config from https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig |
+
 <!-- end: parameters-docs -->
 
 ### Authentication

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "1.7.2"  # DO NOT EDIT, updated automatically
+version = "1.9.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [
@@ -35,7 +35,7 @@ requires-python = ">=3.10"
 dependencies = [
     "docling~=2.38",
     "docling-core>=2.45.0",
-    "docling-jobkit[kfp,rq,vlm]>=1.6.0,<2.0.0",
+    "docling-jobkit[kfp,rq,vlm]>=1.8.0,<2.0.0",
     "fastapi[standard]<0.119.0",  # ~=0.115
     "httpx~=0.28",
     "pydantic~=2.10",
@@ -69,6 +69,9 @@ flash-attn = [
 [dependency-groups]
 dev = [
     "asgi-lifespan~=2.0",
+    "httpx",
+    "pydantic",
+    "pydantic-settings",
     "mypy~=1.11",
     "pre-commit-uv~=4.1",
     "pypdf>=6.0.0",

scripts/update_doc_usage.py

@@ -1,5 +1,5 @@
 import re
-from typing import Annotated, Any, get_args, get_origin
+from typing import Annotated, Any, Union, get_args, get_origin
 
 from pydantic import BaseModel
 
@@ -90,39 +90,75 @@ def _format_type(type_hint: Any) -> str:
     return str(type_hint)
 
 
+def _unroll_types(tp) -> list[type]:
+    """
+    Unrolls typing.Union and typing.Optional types into a flat list of types.
+    """
+    origin = get_origin(tp)
+    if origin is Union:
+        # Recursively unroll each type inside the Union
+        types = []
+        for arg in get_args(tp):
+            types.extend(_unroll_types(arg))
+        # Remove duplicates while preserving order
+        return list(dict.fromkeys(types))
+    else:
+        # If it's not a Union, just return it as a single-element list
+        return [tp]
+
+
 def generate_model_doc(model: type[BaseModel]) -> str:
     """Generate documentation for a Pydantic model."""
-    doc = "\n| Field Name | Type | Description |\n"
-    doc += "|------------|------|-------------|\n"
 
-    for base_model in model.__mro__:
-        # Check if this is a Pydantic model
-        if hasattr(base_model, "model_fields"):
-            # Iterate through fields of this model
-            for field_name, field in base_model.model_fields.items():
-                # Extract description from Annotated field if possible
-                description = field.description or "No description provided."
-                description = format_allowed_values_description(description)
-                description = format_variable_names(description)
+    models_stack = [model]
 
-                # Handle Annotated types
-                original_type = field.annotation
-                if get_origin(original_type) is Annotated:
-                    # Extract base type and additional metadata
-                    type_args = get_args(original_type)
-                    base_type = type_args[0]
-                else:
-                    base_type = original_type
+    doc = ""
+    while models_stack:
+        current_model = models_stack.pop()
 
-                field_type = _format_type(base_type)
-                field_type = format_variable_names(field_type)
+        doc += f"<h4>{current_model.__name__}</h4>\n"
 
-                doc += f"| `{field_name}` | {field_type} | {description} |\n"
+        doc += "\n| Field Name | Type | Description |\n"
+        doc += "|------------|------|-------------|\n"
 
-            # stop iterating the base classes
-            break
+        base_models = []
+        if hasattr(current_model, "__mro__"):
+            base_models = current_model.__mro__
+        else:
+            base_models = [current_model]
 
-    doc += "\n"
+        for base_model in base_models:
+            # Check if this is a Pydantic model
+            if hasattr(base_model, "model_fields"):
+                # Iterate through fields of this model
+                for field_name, field in base_model.model_fields.items():
+                    # Extract description from Annotated field if possible
+                    description = field.description or "No description provided."
+                    description = format_allowed_values_description(description)
+                    description = format_variable_names(description)
+
+                    # Handle Annotated types
+                    original_type = field.annotation
+                    if get_origin(original_type) is Annotated:
+                        # Extract base type and additional metadata
+                        type_args = get_args(original_type)
+                        base_type = type_args[0]
+                    else:
+                        base_type = original_type
+
+                    field_type = _format_type(base_type)
+                    field_type = format_variable_names(field_type)
+
+                    doc += f"| `{field_name}` | {field_type} | {description} |\n"
+
+                    for field_type in _unroll_types(base_type):
+                        if issubclass(field_type, BaseModel):
+                            models_stack.append(field_type)
+
+                # stop iterating the base classes
+                break
+
+        doc += "\n"
     return doc