chore: bump version to 1.7.0 [skip ci]

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

.github/workflows/job-image.yml

@@ -108,6 +108,7 @@ jobs:
           cache-to: type=gha,mode=max
           file: Containerfile
           build-args: ${{ inputs.build_args }}
+          pull: true
       ##
       ## This stage runs after the build, so it leverages all build cache
       ## 
@@ -226,7 +227,8 @@ jobs:
           cache-to: type=gha,mode=max
           file: Containerfile
           build-args: ${{ inputs.build_args }}
+          pull: true
 
-      - name: Remove Local Docker Images
+      - name: Remove local Docker images
         run: |
           docker image prune -af

.pre-commit-config.yaml

@@ -34,6 +34,6 @@ repos:
         files: \.md$
   - repo: https://github.com/astral-sh/uv-pre-commit
     # uv version, https://github.com/astral-sh/uv-pre-commit/releases
-    rev: 0.8.3
+    rev: 0.8.19
     hooks:
       - id: uv-lock

CHANGELOG.md

@@ -1,3 +1,65 @@
+## [v1.7.0](https://github.com/docling-project/docling-serve/releases/tag/v1.7.0) - 2025-10-17
+
+### Feature
+
+* **UI:** Add auto and orcmac options in demo UI ([#408](https://github.com/docling-project/docling-serve/issues/408)) ([`f5af71e`](https://github.com/docling-project/docling-serve/commit/f5af71e8f6de00d7dd702471a3eea2e94d882410))
+* Docling with auto-ocr ([#403](https://github.com/docling-project/docling-serve/issues/403)) ([`d95ea94`](https://github.com/docling-project/docling-serve/commit/d95ea940870af0d8df689061baa50f6026efce28))
+
+### Fix
+
+* Run docling ui behind a reverse proxy using a context path ([#396](https://github.com/docling-project/docling-serve/issues/396)) ([`5344505`](https://github.com/docling-project/docling-serve/commit/53445057184aa731ee7456b33b70bc0ecf82f2a6))
+
+### Docling libraries included in this release:
+- docling 2.57.0
+- docling-core 2.48.4
+- docling-ibm-models 3.9.1
+- docling-jobkit 1.6.0
+- docling-mcp 1.3.2
+- docling-parse 4.5.0
+- docling-serve 1.7.0
+
+## [v1.6.0](https://github.com/docling-project/docling-serve/releases/tag/v1.6.0) - 2025-10-03
+
+### Feature
+
+* Pin new version of jobkit with granite-docling and connectors ([#391](https://github.com/docling-project/docling-serve/issues/391)) ([`0595d31`](https://github.com/docling-project/docling-serve/commit/0595d31d5b357553426215ca6771796a47e41324))
+
+### Fix
+
+* Update locked dependencies ([#392](https://github.com/docling-project/docling-serve/issues/392)) ([`45f0f3c`](https://github.com/docling-project/docling-serve/commit/45f0f3c8f95d418ac30e3744d27d02a63f9e4490))
+* **UI:** Allow both lowercase and uppercase extensions ([#386](https://github.com/docling-project/docling-serve/issues/386)) ([`8b22a39`](https://github.com/docling-project/docling-serve/commit/8b22a391418d22c1a4d706f880341f28702057b5))
+* Correctly raise HTTPException for Gateway Timeout ([#382](https://github.com/docling-project/docling-serve/issues/382)) ([`d4eac05`](https://github.com/docling-project/docling-serve/commit/d4eac053f9ce0a60f9070127335bdd56e193d7fa))
+* Pinning of higher version of dependencies to fix potential security issues ([#363](https://github.com/docling-project/docling-serve/issues/363)) ([`ba61af2`](https://github.com/docling-project/docling-serve/commit/ba61af23591eff200481aa2e532cf7d0701f0ea4))
+
+### Documentation
+
+* Fix docs for websocket breaking condition ([#390](https://github.com/docling-project/docling-serve/issues/390)) ([`f6b5f0e`](https://github.com/docling-project/docling-serve/commit/f6b5f0e06354d2db7d03d274b114499e3407dccf))
+
+### Docling libraries included in this release:
+- docling 2.55.1
+- docling-core 2.48.4
+- docling-ibm-models 3.9.1
+- docling-jobkit 1.6.0
+- docling-mcp 1.3.2
+- docling-parse 4.5.0
+- docling-serve 1.6.0
+
+## [v1.5.1](https://github.com/docling-project/docling-serve/releases/tag/v1.5.1) - 2025-09-17
+
+### Fix
+
+* Remove old dependencies, fixes in docling-parse and more minor dependencies upgrade ([#362](https://github.com/docling-project/docling-serve/issues/362)) ([`513ae0c`](https://github.com/docling-project/docling-serve/commit/513ae0c119b66d3b17cf9a5d371a0f7971f43be7))
+* Updates rapidocr deps ([#361](https://github.com/docling-project/docling-serve/issues/361)) ([`bde0406`](https://github.com/docling-project/docling-serve/commit/bde040661fb65c67699326cd6281c0e6232e26f2))
+
+### Docling libraries included in this release:
+- docling 2.52.0
+- docling-core 2.48.1
+- docling-ibm-models 3.9.1
+- docling-jobkit 1.5.0
+- docling-mcp 1.2.0
+- docling-parse 4.5.0
+- docling-serve 1.5.1
+
 ## [v1.5.0](https://github.com/docling-project/docling-serve/releases/tag/v1.5.0) - 2025-09-09
 
 ### Feature

Containerfile

@@ -1,6 +1,6 @@
 ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
 
-ARG UV_VERSION=0.8.3
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.8.19
 
 ARG UV_SYNC_EXTRA_ARGS=""
 
@@ -25,7 +25,7 @@ RUN /usr/bin/fix-permissions /opt/app-root/src/.cache
 
 ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/
 
-FROM ghcr.io/astral-sh/uv:${UV_VERSION} AS uv_stage
+FROM ${UV_IMAGE} AS uv_stage
 
 ###################################################################################################
 # Docling layer                                                                                   #
@@ -58,7 +58,7 @@ RUN --mount=from=uv_stage,source=/uv,target=/bin/uv \
     uv sync ${UV_SYNC_ARGS} ${UV_SYNC_EXTRA_ARGS} --no-extra flash-attn && \
     FLASH_ATTENTION_SKIP_CUDA_BUILD=TRUE uv sync ${UV_SYNC_ARGS} ${UV_SYNC_EXTRA_ARGS} --no-build-isolation-package=flash-attn
 
-ARG MODELS_LIST="layout tableformer picture_classifier easyocr"
+ARG MODELS_LIST="layout tableformer picture_classifier rapidocr easyocr"
 
 RUN echo "Downloading models..." && \
     HF_HUB_DOWNLOAD_TIMEOUT="90" \

docling_serve/app.py

@@ -46,7 +46,6 @@ from docling_jobkit.datamodel.s3_coords import S3Coordinates
 from docling_jobkit.datamodel.task import Task, TaskSource, TaskType
 from docling_jobkit.datamodel.task_targets import (
     InBodyTarget,
-    TaskTarget,
     ZipTarget,
 )
 from docling_jobkit.orchestrators.base_orchestrator import (
@@ -64,6 +63,7 @@ from docling_serve.datamodel.requests import (
     HttpSourceRequest,
     S3SourceRequest,
     TargetName,
+    TargetRequest,
     make_request_model,
 )
 from docling_serve.datamodel.responses import (
@@ -194,16 +194,25 @@ def create_app():  # noqa: C901
             import gradio as gr
 
             from docling_serve.gradio_ui import ui as gradio_ui
+            from docling_serve.settings import uvicorn_settings
 
             tmp_output_dir = get_scratch() / "gradio"
             tmp_output_dir.mkdir(exist_ok=True, parents=True)
             gradio_ui.gradio_output_dir = tmp_output_dir
+
+            # Build the root_path for Gradio, accounting for UVICORN_ROOT_PATH
+            gradio_root_path = (
+                f"{uvicorn_settings.root_path}/ui"
+                if uvicorn_settings.root_path
+                else "/ui"
+            )
+
             app = gr.mount_gradio_app(
                 app,
                 gradio_ui,
                 path="/ui",
                 allowed_paths=["./logo.png", tmp_output_dir],
-                root_path="/ui",
+                root_path=gradio_root_path,
             )
         except ImportError:
             _log.warning(
@@ -304,7 +313,7 @@ def create_app():  # noqa: C901
         convert_options: ConvertDocumentsRequestOptions,
         chunking_options: BaseChunkerOptions | None,
         chunking_export_options: ChunkingExportOptions | None,
-        target: TaskTarget,
+        target: TargetRequest,
     ) -> Task:
         _log.info(f"Received {len(files)} files for processing.")
 
@@ -455,7 +464,7 @@ def create_app():  # noqa: C901
 
         if not completed:
             # TODO: abort task!
-            return HTTPException(
+            raise HTTPException(
                 status_code=504,
                 detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
             )
@@ -511,7 +520,7 @@ def create_app():  # noqa: C901
 
         if not completed:
             # TODO: abort task!
-            return HTTPException(
+            raise HTTPException(
                 status_code=504,
                 detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
             )
@@ -711,7 +720,7 @@ def create_app():  # noqa: C901
 
             if not completed:
                 # TODO: abort task!
-                return HTTPException(
+                raise HTTPException(
                     status_code=504,
                     detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
                 )
@@ -793,7 +802,7 @@ def create_app():  # noqa: C901
 
             if not completed:
                 # TODO: abort task!
-                return HTTPException(
+                raise HTTPException(
                     status_code=504,
                     detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
                 )

docling_serve/datamodel/requests.py

@@ -13,8 +13,8 @@ from docling_jobkit.datamodel.http_inputs import FileSource, HttpSource
 from docling_jobkit.datamodel.s3_coords import S3Coordinates
 from docling_jobkit.datamodel.task_targets import (
     InBodyTarget,
+    PutTarget,
     S3Target,
-    TaskTarget,
     ZipTarget,
 )
 
@@ -47,12 +47,17 @@ SourceRequestItem = Annotated[
     FileSourceRequest | HttpSourceRequest | S3SourceRequest, Field(discriminator="kind")
 ]
 
+TargetRequest = Annotated[
+    InBodyTarget | ZipTarget | S3Target | PutTarget,
+    Field(discriminator="kind"),
+]
+
 
 ## Complete Source request
 class ConvertDocumentsRequest(BaseModel):
     options: ConvertDocumentsRequestOptions = ConvertDocumentsRequestOptions()
     sources: list[SourceRequestItem]
-    target: TaskTarget = InBodyTarget()
+    target: TargetRequest = InBodyTarget()
 
     @model_validator(mode="after")
     def validate_s3_source_and_target(self) -> Self:
@@ -94,7 +99,7 @@ class BaseChunkDocumentsRequest(BaseModel):
         ),
     ] = False
     target: Annotated[
-        TaskTarget, Field(description="Specification for the type of output target.")
+        TargetRequest, Field(description="Specification for the type of output target.")
     ] = InBodyTarget()
 
 

docling_serve/gradio_ui.py

@@ -4,6 +4,7 @@ import itertools
 import json
 import logging
 import ssl
+import sys
 import tempfile
 import time
 from pathlib import Path
@@ -224,13 +225,17 @@ def auto_set_return_as_file(
 
 def change_ocr_lang(ocr_engine):
     if ocr_engine == "easyocr":
-        return "en,fr,de,es"
+        return gr.update(visible=True, value="en,fr,de,es")
     elif ocr_engine == "tesseract_cli":
-        return "eng,fra,deu,spa"
+        return gr.update(visible=True, value="eng,fra,deu,spa")
     elif ocr_engine == "tesseract":
-        return "eng,fra,deu,spa"
+        return gr.update(visible=True, value="eng,fra,deu,spa")
     elif ocr_engine == "rapidocr":
-        return "english,chinese"
+        return gr.update(visible=True, value="english,chinese")
+    elif ocr_engine == "ocrmac":
+        return gr.update(visible=True, value="fr-FR,de-DE,es-ES,en-US")
+
+    return gr.update(visible=False, value="")
 
 
 def wait_task_finish(auth: str, task_id: str, return_as_file: bool):
@@ -570,14 +575,17 @@ with gr.Blocks(
     with gr.Tab("Convert File"):
         with gr.Row():
             with gr.Column(scale=4):
+                raw_exts = itertools.chain.from_iterable(FormatToExtensions.values())
                 file_input = gr.File(
                     elem_id="file_input_zone",
                     label="Upload File",
                     file_types=[
-                        f".{v}"
-                        for v in itertools.chain.from_iterable(
-                            FormatToExtensions.values()
-                        )
+                        f".{v.lower()}"
+                        for v in raw_exts  # lowercase
+                    ]
+                    + [
+                        f".{v.upper()}"
+                        for v in raw_exts  # uppercase
                     ],
                     file_count="multiple",
                     scale=4,
@@ -633,18 +641,25 @@ with gr.Blocks(
                 ocr = gr.Checkbox(label="Enable OCR", value=True)
                 force_ocr = gr.Checkbox(label="Force OCR", value=False)
             with gr.Column(scale=1):
+                engines_list = [
+                    ("Auto", "auto"),
+                    ("EasyOCR", "easyocr"),
+                    ("Tesseract", "tesseract"),
+                    ("RapidOCR", "rapidocr"),
+                ]
+                if sys.platform == "darwin":
+                    engines_list.append(("OCRMac", "ocrmac"))
+
                 ocr_engine = gr.Radio(
-                    [
-                        ("EasyOCR", "easyocr"),
-                        ("Tesseract", "tesseract"),
-                        ("RapidOCR", "rapidocr"),
-                    ],
+                    engines_list,
                     label="OCR Engine",
-                    value="easyocr",
+                    value="auto",
                 )
             with gr.Column(scale=1, min_width=200):
                 ocr_lang = gr.Textbox(
-                    label="OCR Language (beware of the format)", value="en,fr,de,es"
+                    label="OCR Language (beware of the format)",
+                    value="en,fr,de,es",
+                    visible=False,
                 )
             ocr_engine.change(change_ocr_lang, inputs=[ocr_engine], outputs=[ocr_lang])
         with gr.Row():

docs/usage.md

@@ -433,7 +433,7 @@ with connect(uri) as websocket:
             payload = json.loads(message)
             if payload["message"] == "error":
                 break
-            if payload["message"] == "error" and payload["task"]["task_status"] in ("success", "failure"):
+            if payload["message"] == "update" and payload["task"]["task_status"] in ("success", "failure"):
                 break
         except:
           break

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "1.5.0"  # DO NOT EDIT, updated automatically
+version = "1.7.0"  # 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]>=1.5.0,<2.0.0",
+    "docling-jobkit[kfp,rq,vlm]>=1.6.0,<2.0.0",
     "fastapi[standard]~=0.115",
     "httpx~=0.28",
     "pydantic~=2.10",
@@ -50,15 +50,17 @@ dependencies = [
 
 [project.optional-dependencies]
 ui = [
-    "gradio~=5.9",
-    "pydantic<2.11.0",  # fix compatibility between gradio and new pydantic 2.11
+    "gradio>=5.23.2,<6.0.0",
 ]
 tesserocr = [
     "tesserocr~=2.7"
 ]
+easyocr = [
+    "easyocr>=1.7",
+]
 rapidocr = [
-    "rapidocr-onnxruntime~=1.4; python_version<'3.13'",
-    "onnxruntime~=1.7",
+    "rapidocr (>=3.3,<4.0.0) ; python_version < '3.14'",
+    "onnxruntime (>=1.7.0,<2.0.0)",
 ]
 flash-attn = [
   "flash-attn~=2.8.2; sys_platform == 'linux' and platform_machine == 'x86_64'"
@@ -87,10 +89,10 @@ cpu = [
   "torchvision>=0.22.1",
 ]
 
-cu124 = [
-  "torch>=2.6.0",
-  "torchvision>=0.21.0",
-]
+# cu124 = [
+#   "torch>=2.6.0",
+#   "torchvision>=0.21.0",
+# ]
 
 cu126 = [
   "torch>=2.7.1",
@@ -115,7 +117,7 @@ conflicts = [
   [
     { group = "pypi" },
     { group = "cpu" },
-    { group = "cu124" },
+    # { group = "cu124" },
     { group = "cu126" },
     { group = "cu128" },
     { group = "rocm" },
@@ -123,14 +125,15 @@ conflicts = [
 ]
 environments = ["sys_platform != 'darwin' or platform_machine != 'x86_64'"]
 override-dependencies = [
-  "urllib3~=2.0"
+  "urllib3~=2.0",
+  "xgrammar>=0.1.24"
 ]
 
 [tool.uv.sources]
 torch = [
   { index = "pytorch-pypi", group = "pypi" },
   { index = "pytorch-cpu", group = "cpu" },
-  { index = "pytorch-cu124", group = "cu124", marker = "sys_platform == 'linux'" },
+  # { index = "pytorch-cu124", group = "cu124", marker = "sys_platform == 'linux'" },
   { index = "pytorch-cu126", group = "cu126", marker = "sys_platform == 'linux'" },
   { index = "pytorch-cu128", group = "cu128", marker = "sys_platform == 'linux'" },
   { index = "pytorch-rocm", group = "rocm", marker = "sys_platform == 'linux'" },
@@ -139,7 +142,7 @@ torch = [
 torchvision = [
   { index = "pytorch-pypi", group = "pypi" },
   { index = "pytorch-cpu", group = "cpu" },
-  { index = "pytorch-cu124", group = "cu124", marker = "sys_platform == 'linux'" },
+  # { index = "pytorch-cu124", group = "cu124", marker = "sys_platform == 'linux'" },
   { index = "pytorch-cu126", group = "cu126", marker = "sys_platform == 'linux'" },
   { index = "pytorch-cu128", group = "cu128", marker = "sys_platform == 'linux'" },
   { index = "pytorch-rocm", group = "rocm", marker = "sys_platform == 'linux'" },
@@ -162,10 +165,10 @@ name = "pytorch-cpu"
 url = "https://download.pytorch.org/whl/cpu"
 explicit = true
 
-[[tool.uv.index]]
-name = "pytorch-cu124"
-url = "https://download.pytorch.org/whl/cu124"
-explicit = true
+# [[tool.uv.index]]
+# name = "pytorch-cu124"
+# url = "https://download.pytorch.org/whl/cu124"
+# explicit = true
 
 [[tool.uv.index]]
 name = "pytorch-cu126"