chore: bump version to 0.16.1 [skip ci]

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

CHANGELOG.md

@@ -1,3 +1,17 @@
+## [v0.16.1](https://github.com/docling-project/docling-serve/releases/tag/v0.16.1) - 2025-07-07
+
+### Fix
+
+* Upgrade deps including, docling v2.40.0 with locks in models init ([#264](https://github.com/docling-project/docling-serve/issues/264)) ([`bfde1a0`](https://github.com/docling-project/docling-serve/commit/bfde1a0991c2da53b72c4f131ff74fa10f6340de))
+* Missing tesseract osd ([#263](https://github.com/docling-project/docling-serve/issues/263)) ([`eb3892e`](https://github.com/docling-project/docling-serve/commit/eb3892ee141eb2c941d580b095d8a266f2d2610c))
+* Properly load models at boot ([#244](https://github.com/docling-project/docling-serve/issues/244)) ([`149a8cb`](https://github.com/docling-project/docling-serve/commit/149a8cb1c0a16c1e0b7d17f40b88b4d6e8f0109d))
+
+### Documentation
+
+* Fix typo ([#259](https://github.com/docling-project/docling-serve/issues/259)) ([`93b8471`](https://github.com/docling-project/docling-serve/commit/93b84712b2c6d180908a197847b52b217a7ff05f))
+* Change the doc example ([#258](https://github.com/docling-project/docling-serve/issues/258)) ([`c45b937`](https://github.com/docling-project/docling-serve/commit/c45b93706466a073ab4a5c75aa8a267110873e26))
+* Update typo ([#247](https://github.com/docling-project/docling-serve/issues/247)) ([`50e431f`](https://github.com/docling-project/docling-serve/commit/50e431f30fbffa33f43727417fe746d20cbb9d6b))
+
 ## [v0.16.0](https://github.com/docling-project/docling-serve/releases/tag/v0.16.0) - 2025-06-25
 
 ### Feature

docling_serve/app.py

@@ -99,7 +99,8 @@ async def lifespan(app: FastAPI):
     scratch_dir = get_scratch()
 
     # Warm up processing cache
-    await orchestrator.warm_up_caches()
+    if docling_serve_settings.load_models_at_boot:
+        await orchestrator.warm_up_caches()
 
     # Start the background queue processor
     queue_task = asyncio.create_task(orchestrator.process_queue())

docling_serve/engines/async_local/orchestrator.py

@@ -3,6 +3,8 @@ import logging
 import uuid
 from typing import Optional
 
+from docling.datamodel.base_models import InputFormat
+
 from docling_serve.datamodel.convert import ConvertDocumentsOptions
 from docling_serve.datamodel.task import Task, TaskSource
 from docling_serve.docling_conversion import get_converter, get_pdf_pipeline_opts
@@ -54,4 +56,5 @@ class AsyncLocalOrchestrator(BaseAsyncOrchestrator):
     async def warm_up_caches(self):
         # Converter with default options
         pdf_format_option = get_pdf_pipeline_opts(ConvertDocumentsOptions())
-        get_converter(pdf_format_option)
+        converter = get_converter(pdf_format_option)
+        converter.initialize_pipeline(InputFormat.PDF)

docling_serve/settings.py

@@ -41,6 +41,7 @@ class DoclingServeSettings(BaseSettings):
     scratch_path: Optional[Path] = None
     single_use_results: bool = True
     result_removal_delay: float = 300  # 5 minutes
+    load_models_at_boot: bool = True
     options_cache_size: int = 2
     enable_remote_services: bool = False
     allow_external_plugins: bool = False

docs/configuration.md

@@ -7,7 +7,7 @@ server and the actual app-specific configurations.
 
  > [!WARNING]
 > When the server is running with `reload` or with multiple `workers`, uvicorn
-> will spawn multiple subprocessed. This invalides all the values configured
+> will spawn multiple subprocessed. This invalidates all the values configured
 > via the CLI command line options. Please use environment variables in this
 > type of deployments.
 
@@ -47,6 +47,7 @@ THe following table describes the options to configure the Docling Serve app.
 |  | `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_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_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. |

docs/usage.md

@@ -19,7 +19,7 @@ On top of the source of file (see below), both endpoints support the same parame
 - `table_mode` (str): Table mode to use. Allowed values: `fast`, `accurate`. Defaults to `fast`.
 - `abort_on_error` (bool): If enabled, abort on error. Defaults to false.
 - `return_as_file` (boo): If enabled, return the output as a file. Defaults to false.
-- `md_page_break_placeholder` (str): Add this placeholder betweek pages in the markdown output.
+- `md_page_break_placeholder` (str): Add this placeholder between pages in the markdown output.
 - `do_table_structure` (bool): If enabled, the table structure will be extracted. Defaults to true.
 - `do_code_enrichment` (bool): If enabled, perform OCR code enrichment. Defaults to false.
 - `do_formula_enrichment` (bool): If enabled, perform formula OCR, return LaTeX code. Defaults to false.
@@ -288,33 +288,42 @@ The api option is specified with:
 
 Example URLs are:
 
-- `http://localhost:8000/v1/chat/completions` for the local vllm api, with example `params`:
+- `http://localhost:8000/v1/chat/completions` for the local vllm api, with example `picture_description_api`:
   - the `HuggingFaceTB/SmolVLM-256M-Instruct` model
 
     ```json
     {
+      "url": "http://localhost:8000/v1/chat/completions",
+      "params": {
         "model": "HuggingFaceTB/SmolVLM-256M-Instruct",
         "max_completion_tokens": 200,
+      }
     }
     ```
-  
+
   - the `ibm-granite/granite-vision-3.2-2b` model
 
     ```json
     {
+      "url": "http://localhost:8000/v1/chat/completions",
+      "params": {
         "model": "ibm-granite/granite-vision-3.2-2b",
         "max_completion_tokens": 200,
+      }
     }
     ```
 
-- `http://localhost:11434/v1/chat/completions` for the local ollama api, with example `params`:
+- `http://localhost:11434/v1/chat/completions` for the local ollama api, with example `picture_description_api`:
   - the `granite3.2-vision:2b` model
 
     ```json
     {
+      "url": "http://localhost:11434/v1/chat/completions",
+      "params": {
         "model": "granite3.2-vision:2b"
+      }
     }
-    ```  
+    ```
 
 Note that when using `picture_description_api`, the server must be launched with `DOCLING_SERVE_ENABLE_REMOTE_SERVICES=true`.
 

os-packages.txt

@@ -1,6 +1,7 @@
 tesseract
 tesseract-devel
 tesseract-langpack-eng
+tesseract-osd
 leptonica-devel
 libglvnd-glx
 glib2

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.16.0"  # DO NOT EDIT, updated automatically
+version = "0.16.1"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [