chore: bump version to 0.10.0 [skip ci]

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

.flake8

@@ -1,7 +0,0 @@
-[flake8]
-max-line-length = 88
-exclude = test/*
-max-complexity = 18
-docstring-convention = google
-ignore = W503,E203
-classmethod-decorators = classmethod,validator

.github/SECURITY.md

@@ -20,4 +20,4 @@ After the initial reply to your report, the security team will keep you informed
 
 ## Security Alerts
 
-We will send announcements of security vulnerabilities and steps to remediate on the [Docling announcements](https://github.com/DS4SD/docling/discussions/categories/announcements).
+We will send announcements of security vulnerabilities and steps to remediate on the [Docling announcements](https://github.com/docling-project/docling/discussions/categories/announcements).

.github/scripts/release.sh

@@ -11,6 +11,7 @@ CHGLOG_FILE="${CHGLOG_FILE:-CHANGELOG.md}"
 
 # update package version
 uvx --from=toml-cli toml set --toml-path=pyproject.toml project.version "${TARGET_VERSION}"
+uv lock --upgrade-package docling-serve
 
 # collect release notes
 REL_NOTES=$(mktemp)
@@ -30,7 +31,7 @@ mv "${TMP_CHGLOG}" "${CHGLOG_FILE}"
 # push changes
 git config --global user.name 'github-actions[bot]'
 git config --global user.email 'github-actions[bot]@users.noreply.github.com'
-git add pyproject.toml "${CHGLOG_FILE}"
+git add pyproject.toml uv.lock "${CHGLOG_FILE}"
 COMMIT_MSG="chore: bump version to ${TARGET_VERSION} [skip ci]"
 git commit -m "${COMMIT_MSG}"
 git push origin main

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

@@ -13,15 +13,15 @@ jobs:
     strategy:
       matrix:
         spec:
-          - name: ds4sd/docling-serve
+          - name: docling-project/docling-serve
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
             platforms: linux/amd64, linux/arm64
-          - name: ds4sd/docling-serve-cpu
+          - name: docling-project/docling-serve-cpu
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cu124
             platforms: linux/amd64, linux/arm64
-          - name: ds4sd/docling-serve-cu124
+          - name: docling-project/docling-serve-cu124
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cpu
             platforms: linux/amd64

.github/workflows/ci.yml

@@ -8,7 +8,7 @@ on:
 
 jobs:
   code-checks:
-    # if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'DS4SD/docling-serve' && github.event.pull_request.head.repo.full_name != 'ds4sd/docling-serve') }}
+    # if: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'docling-project/docling-serve' && github.event.pull_request.head.repo.full_name != 'docling-project/docling-serve') }}
     uses: ./.github/workflows/job-checks.yml
     permissions:
       packages: write

.github/workflows/images.yml

@@ -17,15 +17,15 @@ jobs:
     strategy:
       matrix:
         spec:
-          - name: ds4sd/docling-serve
+          - name: docling-project/docling-serve
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
             platforms: linux/amd64, linux/arm64
-          - name: ds4sd/docling-serve-cpu
+          - name: docling-project/docling-serve-cpu
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cu124
             platforms: linux/amd64, linux/arm64
-          - name: ds4sd/docling-serve-cu124
+          - name: docling-project/docling-serve-cu124
             build_args: |
               UV_SYNC_EXTRA_ARGS=--no-extra cpu
             platforms: linux/amd64

.github/workflows/job-build.yml

@@ -0,0 +1,29 @@
+name: Run checks
+
+on:
+  workflow_call:
+
+jobs:
+  build-package:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install dependencies
+        run: uv sync --all-extras --no-extra cu124
+      - name: Build package
+        run: uv build
+      - name: Check content of wheel
+        run: unzip -l dist/*.whl
+      - name: Store the distribution packages
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/

.github/workflows/job-checks.yml

@@ -16,10 +16,45 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true
+
+      - name: pre-commit cache key
+        run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> "$GITHUB_ENV"
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
+
       - name: Install dependencies
-        run: uv sync --all-extras --no-extra cu124
+        run: uv sync --frozen --all-extras --no-extra cu124
+
       - name: Run styling check
-        run: uv run --no-sync pre-commit run --all-files
+        run: pre-commit run --all-files
+
+  build-package:
+    uses: ./.github/workflows/job-build.yml
+
+  test-package:
+    needs:
+      - build-package
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.12']
+    steps:
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: Install package
+        run: uv pip install dist/*.whl
+      - name: Create the server
+        run: python -c 'from docling_serve.app import create_app; create_app()'
 
   markdown-lint:
     runs-on: ubuntu-latest

.github/workflows/pypi.yml

@@ -8,7 +8,13 @@ permissions:
   contents: read
 
 jobs:
+
+  build-package:
+    uses: ./.github/workflows/job-build.yml
+
   build-and-publish:
+    needs:
+      - build-package
     runs-on: ubuntu-latest
     environment:
       name: pypi
@@ -16,15 +22,11 @@ jobs:
     permissions:
       id-token: write  # IMPORTANT: mandatory for trusted publishing
     steps:
-      - uses: actions/checkout@v4
-      - name: Install uv and set the python version
-        uses: astral-sh/setup-uv@v5
+      - name: Download all the dists
+        uses: actions/download-artifact@v4
         with:
-          enable-cache: true
-      - name: Install dependencies
-        run: uv sync --all-extras --no-extra cu124
-      - name: Build
-        run: uv build
+          name: python-package-distributions
+          path: dist/
       - name: Publish distribution 📦 to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:

.markdownlint-cli2.yaml

@@ -3,7 +3,7 @@ config:
   no-emphasis-as-header: false
   first-line-heading: false
   MD033:
-    allowed_elements: ["details", "summary"]
+    allowed_elements: ["details", "summary", "br", "a", "b", "p", "img"]
   MD024:
     siblings_only: true
 globs:

.pre-commit-config.yaml

@@ -5,10 +5,14 @@ repos:
     hooks:
       # Run the Ruff formatter.
       - id: ruff-format
+        name: "Ruff formatter"
         args: [--config=pyproject.toml]
+        files: '^(docling_serve|tests).*\.(py|ipynb)$'
       # Run the Ruff linter.
       - id: ruff
+        name: "Ruff linter"
         args: [--exit-non-zero-on-fix, --fix, --config=pyproject.toml]
+        files: '^(docling_serve|tests).*\.(py|ipynb)$'
   - repo: local
     hooks:
       - id: system

CHANGELOG.md

@@ -1,30 +1,112 @@
-## [v0.5.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.5.0) - 2025-03-07
+## [v0.10.0](https://github.com/docling-project/docling-serve/releases/tag/v0.10.0) - 2025-04-28
 
 ### Feature
 
-* Async api ([#60](https://github.com/DS4SD/docling-serve/issues/60)) ([`82f8900`](https://github.com/DS4SD/docling-serve/commit/82f890019745859699c1b01f9ccfb64cb7e37906))
-* Display version in fastapi docs ([#78](https://github.com/DS4SD/docling-serve/issues/78)) ([`ed851c9`](https://github.com/DS4SD/docling-serve/commit/ed851c95fee5f59305ddc3dcd5c09efce618470b))
+* Add support for file upload and return as file in async endpoints ([#152](https://github.com/docling-project/docling-serve/issues/152)) ([`c65f3c6`](https://github.com/docling-project/docling-serve/commit/c65f3c654c76c6b64b6aada1f0a153d74789d629))
+
+### Documentation
+
+* Fix new default pdf_backend ([#158](https://github.com/docling-project/docling-serve/issues/158)) ([`829effe`](https://github.com/docling-project/docling-serve/commit/829effec1a1b80320ccaf2c501be8015169b6fa3))
+* Fixing small typo in docs ([#155](https://github.com/docling-project/docling-serve/issues/155)) ([`14bafb2`](https://github.com/docling-project/docling-serve/commit/14bafb26286b94f80b56846c50d6e9a6d99a9763))
+
+## [v0.9.0](https://github.com/docling-project/docling-serve/releases/tag/v0.9.0) - 2025-04-25
+
+### Feature
+
+* Expose picture description options ([#148](https://github.com/docling-project/docling-serve/issues/148)) ([`4c9571a`](https://github.com/docling-project/docling-serve/commit/4c9571a052d5ec0044e49225bc5615e13cdb0a56))
+* Add parameters for Kubeflow pipeline engine (WIP) ([#107](https://github.com/docling-project/docling-serve/issues/107)) ([`26bef5b`](https://github.com/docling-project/docling-serve/commit/26bef5bec060f0afd8d358816b68c3f2c0dd4bc2))
 
 ### Fix
 
-* Remove uv from image, merge ARG and ENV declarations ([#57](https://github.com/DS4SD/docling-serve/issues/57)) ([`c95db36`](https://github.com/DS4SD/docling-serve/commit/c95db3643807a4dfb96d93c8e10d6eb486c49a30))
-* **docs:** Remove comma in convert/source curl example ([#73](https://github.com/DS4SD/docling-serve/issues/73)) ([`05df073`](https://github.com/DS4SD/docling-serve/commit/05df0735d35a589bdc2a11fcdd764a10f700cb6f))
+* Produce image artifacts in referenced mode ([#151](https://github.com/docling-project/docling-serve/issues/151)) ([`71c5fae`](https://github.com/docling-project/docling-serve/commit/71c5fae505366459fd481d2ecdabc5ebed94d49c))
 
-## [v0.4.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.4.0) - 2025-02-26
+### Documentation
+
+* Vlm and picture description options ([#149](https://github.com/docling-project/docling-serve/issues/149)) ([`91956cb`](https://github.com/docling-project/docling-serve/commit/91956cbf4e91cf82bb4d54ace397cdbbfaf594ba))
+
+## [v0.8.0](https://github.com/docling-project/docling-serve/releases/tag/v0.8.0) - 2025-04-22
 
 ### Feature
 
-* New container images ([#68](https://github.com/DS4SD/docling-serve/issues/68)) ([`7e6d9cd`](https://github.com/DS4SD/docling-serve/commit/7e6d9cdef398df70a5b4d626aeb523c428c10d56))
-* Render DoclingDocument with npm docling-components in the example UI ([#65](https://github.com/DS4SD/docling-serve/issues/65)) ([`c430d9b`](https://github.com/DS4SD/docling-serve/commit/c430d9b1a162ab29104d86ebaa1ac5a5488b1f09))
-
-## [v0.3.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.3.0) - 2025-02-19
-
-### Feature
-
-* Add new docling-serve cli ([#50](https://github.com/DS4SD/docling-serve/issues/50)) ([`ec33a61`](https://github.com/DS4SD/docling-serve/commit/ec33a61faa7846b9b7998fbf557ebe39a3b800f6))
+* 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
 
-* Set DOCLING_SERVE_ARTIFACTS_PATH in images ([#53](https://github.com/DS4SD/docling-serve/issues/53)) ([`4877248`](https://github.com/DS4SD/docling-serve/commit/487724836896576ca4f98e84abf15fd1c383bec8))
-* Set root UI path when behind proxy ([#38](https://github.com/DS4SD/docling-serve/issues/38)) ([`c64a450`](https://github.com/DS4SD/docling-serve/commit/c64a450bf9ba9947ab180e92bef2763ff710b210))
-* Support python 3.13 and docling updates and switch to uv ([#48](https://github.com/DS4SD/docling-serve/issues/48)) ([`ae3b490`](https://github.com/DS4SD/docling-serve/commit/ae3b4906f1c0829b1331ea491f3518741cabff71))
+* **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
+
+* Expose TLS settings and example deploy with oauth-proxy ([#112](https://github.com/docling-project/docling-serve/issues/112)) ([`7a0faba`](https://github.com/docling-project/docling-serve/commit/7a0fabae07020c2659dbb22c3b0359909051a74c))
+* Offline static files ([#109](https://github.com/docling-project/docling-serve/issues/109)) ([`68772bb`](https://github.com/docling-project/docling-serve/commit/68772bb6f0a87b71094a08ff851f5754c6ca6163))
+* Update to Docling 2.28 ([#106](https://github.com/docling-project/docling-serve/issues/106)) ([`20ec87a`](https://github.com/docling-project/docling-serve/commit/20ec87a63a99145bc0ad7931549af8a0c30db641))
+
+### Fix
+
+* Move ARGs to prevent cache invalidation ([#104](https://github.com/docling-project/docling-serve/issues/104)) ([`e30f458`](https://github.com/docling-project/docling-serve/commit/e30f458923d34c169db7d5a5c296848716e8cac4))
+
+## [v0.6.0](https://github.com/docling-project/docling-serve/releases/tag/v0.6.0) - 2025-03-17
+
+### Feature
+
+* Expose options for new features ([#92](https://github.com/docling-project/docling-serve/issues/92)) ([`ec57b52`](https://github.com/docling-project/docling-serve/commit/ec57b528ed3f8e7b9604ff4cdf06da3d52c714dd))
+
+### Fix
+
+* Allow changes in CORS settings ([#100](https://github.com/docling-project/docling-serve/issues/100)) ([`422c402`](https://github.com/docling-project/docling-serve/commit/422c402bab7f05e46274ede11f234a19a62e093e))
+* Avoid exploding options cache using lru and expose size parameter ([#101](https://github.com/docling-project/docling-serve/issues/101)) ([`ea09028`](https://github.com/docling-project/docling-serve/commit/ea090288d3eec4ea8fbdcd32a6a497a99c89189d))
+* Increase timeout_keep_alive and allow parameter changes ([#98](https://github.com/docling-project/docling-serve/issues/98)) ([`07c48ed`](https://github.com/docling-project/docling-serve/commit/07c48edd5d9437219d9623e3d05bc5166c5bb85a))
+* Add warning when using incompatible parameters ([#99](https://github.com/docling-project/docling-serve/issues/99)) ([`a212547`](https://github.com/docling-project/docling-serve/commit/a212547d28d6588c65e52000dc7bc04f3f77e69e))
+* **ui:** Use --port parameter and avoid failing when image is not found ([#97](https://github.com/docling-project/docling-serve/issues/97)) ([`c76daac`](https://github.com/docling-project/docling-serve/commit/c76daac70c87da412f791666881e48b74688b060))
+
+### Documentation
+
+* Simplify README and move details to docs ([#102](https://github.com/docling-project/docling-serve/issues/102)) ([`fd8e40a`](https://github.com/docling-project/docling-serve/commit/fd8e40a00849771263d9b75b9a56f6caeccb8517))
+
+## [v0.5.1](https://github.com/docling-project/docling-serve/releases/tag/v0.5.1) - 2025-03-10
+
+### Fix
+
+* Submodules in wheels ([#85](https://github.com/docling-project/docling-serve/issues/85)) ([`a92ad48`](https://github.com/docling-project/docling-serve/commit/a92ad48b287bfcb134011dc0fc3f91ee04e067ee))
+
+## [v0.5.0](https://github.com/docling-project/docling-serve/releases/tag/v0.5.0) - 2025-03-07
+
+### Feature
+
+* Async api ([#60](https://github.com/docling-project/docling-serve/issues/60)) ([`82f8900`](https://github.com/docling-project/docling-serve/commit/82f890019745859699c1b01f9ccfb64cb7e37906))
+* Display version in fastapi docs ([#78](https://github.com/docling-project/docling-serve/issues/78)) ([`ed851c9`](https://github.com/docling-project/docling-serve/commit/ed851c95fee5f59305ddc3dcd5c09efce618470b))
+
+### Fix
+
+* Remove uv from image, merge ARG and ENV declarations ([#57](https://github.com/docling-project/docling-serve/issues/57)) ([`c95db36`](https://github.com/docling-project/docling-serve/commit/c95db3643807a4dfb96d93c8e10d6eb486c49a30))
+* **docs:** Remove comma in convert/source curl example ([#73](https://github.com/docling-project/docling-serve/issues/73)) ([`05df073`](https://github.com/docling-project/docling-serve/commit/05df0735d35a589bdc2a11fcdd764a10f700cb6f))
+
+## [v0.4.0](https://github.com/docling-project/docling-serve/releases/tag/v0.4.0) - 2025-02-26
+
+### Feature
+
+* New container images ([#68](https://github.com/docling-project/docling-serve/issues/68)) ([`7e6d9cd`](https://github.com/docling-project/docling-serve/commit/7e6d9cdef398df70a5b4d626aeb523c428c10d56))
+* Render DoclingDocument with npm docling-components in the example UI ([#65](https://github.com/docling-project/docling-serve/issues/65)) ([`c430d9b`](https://github.com/docling-project/docling-serve/commit/c430d9b1a162ab29104d86ebaa1ac5a5488b1f09))
+
+## [v0.3.0](https://github.com/docling-project/docling-serve/releases/tag/v0.3.0) - 2025-02-19
+
+### Feature
+
+* Add new docling-serve cli ([#50](https://github.com/docling-project/docling-serve/issues/50)) ([`ec33a61`](https://github.com/docling-project/docling-serve/commit/ec33a61faa7846b9b7998fbf557ebe39a3b800f6))
+
+### Fix
+
+* Set DOCLING_SERVE_ARTIFACTS_PATH in images ([#53](https://github.com/docling-project/docling-serve/issues/53)) ([`4877248`](https://github.com/docling-project/docling-serve/commit/487724836896576ca4f98e84abf15fd1c383bec8))
+* Set root UI path when behind proxy ([#38](https://github.com/docling-project/docling-serve/issues/38)) ([`c64a450`](https://github.com/docling-project/docling-serve/commit/c64a450bf9ba9947ab180e92bef2763ff710b210))
+* Support python 3.13 and docling updates and switch to uv ([#48](https://github.com/docling-project/docling-serve/issues/48)) ([`ae3b490`](https://github.com/docling-project/docling-serve/commit/ae3b4906f1c0829b1331ea491f3518741cabff71))

CONTRIBUTING.md

@@ -3,13 +3,13 @@
 Our project welcomes external contributions. If you have an itch, please feel
 free to scratch it.
 
-To contribute code or documentation, please submit a [pull request](https://github.com/DS4SD/docling-serve/pulls).
+To contribute code or documentation, please submit a [pull request](https://github.com/docling-project/docling-serve/pulls).
 
 A good way to familiarize yourself with the codebase and contribution process is
-to look for and tackle low-hanging fruit in the [issue tracker](https://github.com/DS4SD/docling-serve/issues).
+to look for and tackle low-hanging fruit in the [issue tracker](https://github.com/docling-project/docling-serve/issues).
 Before embarking on a more ambitious contribution, please quickly [get in touch](#communication) with us.
 
-For general questions or support requests, please refer to the [discussion section](https://github.com/DS4SD/docling-serve/discussions).
+For general questions or support requests, please refer to the [discussion section](https://github.com/docling-project/docling-serve/discussions).
 
 **Note: We appreciate your effort, and want to avoid a situation where a contribution
 requires extensive rework (by you or by us), sits in backlog for a long time, or
@@ -17,14 +17,14 @@ cannot be accepted at all!**
 
 ### Proposing new features
 
-If you would like to implement a new feature, please [raise an issue](https://github.com/DS4SD/docling-serve/issues)
+If you would like to implement a new feature, please [raise an issue](https://github.com/docling-project/docling-serve/issues)
 before sending a pull request so the feature can be discussed. This is to avoid
 you wasting your valuable time working on a feature that the project developers
 are not interested in accepting into the code base.
 
 ### Fixing bugs
 
-If you would like to fix a bug, please [raise an issue](https://github.com/DS4SD/docling-serve/issues) before sending a
+If you would like to fix a bug, please [raise an issue](https://github.com/docling-project/docling-serve/issues) before sending a
 pull request so it can be tracked.
 
 ### Merge approval
@@ -73,7 +73,7 @@ git commit -s
 
 ## Communication
 
-Please feel free to connect with us using the [discussion section](https://github.com/DS4SD/docling-serve/discussions).
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling-serve/discussions).
 
 ## Developing
 
@@ -142,8 +142,7 @@ poetry add NAME
 
 We use the following tools to enforce code style:
 
-- iSort, to sort imports
-- Black, to format code
+- ruff, to sort imports and format code
 
 We run a series of checks on the code base on every commit, using `pre-commit`. To install the hooks, run:
 
@@ -157,4 +156,4 @@ To run the checks on-demand, run:
 pre-commit run --all-files
 ```
 
-Note: Checks like `Black` and `isort` will "fail" if they modify files. This is because `pre-commit` doesn't like to see files modified by their Hooks. In these cases, `git add` the modified files and `git commit` again.
+Note: Formatting checks like `ruff` will "fail" if they modify files. This is because `pre-commit` doesn't like to see files modified by their Hooks. In these cases, `git add` the modified files and `git commit` again.

Containerfile

@@ -2,9 +2,6 @@ ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
 
 FROM ${BASE_IMAGE}
 
-ARG MODELS_LIST="layout tableformer picture_classifier easyocr" \
-    UV_SYNC_EXTRA_ARGS=""
-
 USER 0
 
 ###################################################################################################
@@ -20,6 +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/
 
 ###################################################################################################
@@ -41,23 +40,29 @@ ENV \
     UV_PROJECT_ENVIRONMENT=/opt/app-root \
     DOCLING_SERVE_ARTIFACTS_PATH=/opt/app-root/src/.cache/docling/models
 
+ARG UV_SYNC_EXTRA_ARGS=""
+
 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"
 
 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
 

Makefile

@@ -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
@@ -27,23 +28,23 @@ md-lint-file:
 .PHONY: docling-serve-image
 docling-serve-image: Containerfile
 	$(ECHO_PREFIX) printf "  %-12s Containerfile\n" "[docling-serve]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu" -f Containerfile -t ghcr.io/ds4sd/docling-serve:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) ghcr.io/ds4sd/docling-serve:main
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve:$(TAG) quay.io/ds4sd/docling-serve:main
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu" -f Containerfile -t ghcr.io/docling-project/docling-serve:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) ghcr.io/docling-project/docling-serve:$(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]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124" -f Containerfile -t ghcr.io/ds4sd/docling-serve-cpu:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cpu:$(TAG) ghcr.io/ds4sd/docling-serve-cpu:main
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cpu:$(TAG) quay.io/ds4sd/docling-serve-cpu:main
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cu124" -f Containerfile -t ghcr.io/docling-project/docling-serve-cpu:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) ghcr.io/docling-project/docling-serve-cpu:$(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]"
-	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cpu" -f Containerfile --platform linux/amd64 -t ghcr.io/ds4sd/docling-serve-cu124:$(TAG) .
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cu124:$(TAG) ghcr.io/ds4sd/docling-serve-cu124:main
-	$(CMD_PREFIX) docker tag ghcr.io/ds4sd/docling-serve-cu124:$(TAG) quay.io/ds4sd/docling-serve-cu124:main
+	$(CMD_PREFIX) docker build --load --build-arg "UV_SYNC_EXTRA_ARGS=--no-extra cpu" -f Containerfile --platform linux/amd64 -t ghcr.io/docling-project/docling-serve-cu124:$(TAG) .
+	$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) ghcr.io/docling-project/docling-serve-cu124:$(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
@@ -66,7 +67,7 @@ action-lint: .action-lint ##      Lint GitHub Action workflows
 md-lint: .md-lint ##      Lint markdown files
 .md-lint: $(wildcard */**/*.md) | md-lint-file
 	$(ECHO_PREFIX) printf "  %-12s ./...\n" "[MD LINT]"
-	$(CMD_PREFIX) docker run --rm -v $$(pwd):/workdir davidanson/markdownlint-cli2:v0.14.0 "**/*.md"
+	$(CMD_PREFIX) docker run --rm -v $$(pwd):/workdir davidanson/markdownlint-cli2:v0.16.0 "**/*.md" "#.venv"
 	$(CMD_PREFIX) touch $@
 
 .PHONY: py-Lint
@@ -84,11 +85,11 @@ run-docling-cpu: ## Run the docling-serve container with CPU support and assign
 	$(ECHO_PREFIX) printf "  %-12s Removing existing container if it exists...\n" "[CLEANUP]"
 	$(CMD_PREFIX) docker rm -f docling-serve-cpu 2>/dev/null || true
 	$(ECHO_PREFIX) printf "  %-12s Running docling-serve container with CPU support on port 5001...\n" "[RUN CPU]"
-	$(CMD_PREFIX) docker run -it --name docling-serve-cpu -p 5001:5001 ghcr.io/ds4sd/docling-serve-cpu:main
+	$(CMD_PREFIX) docker run -it --name docling-serve-cpu -p 5001:5001 ghcr.io/docling-project/docling-serve-cpu:main
 
 .PHONY: run-docling-gpu
 run-docling-gpu: ## Run the docling-serve container with GPU support and assign a container name
 	$(ECHO_PREFIX) printf "  %-12s Removing existing container if it exists...\n" "[CLEANUP]"
 	$(CMD_PREFIX) docker rm -f docling-serve-gpu 2>/dev/null || true
 	$(ECHO_PREFIX) printf "  %-12s Running docling-serve container with GPU support on port 5001...\n" "[RUN GPU]"
-	$(CMD_PREFIX) docker run -it --name docling-serve-gpu -p 5001:5001 ghcr.io/ds4sd/docling-serve:main
+	$(CMD_PREFIX) docker run -it --name docling-serve-gpu -p 5001:5001 ghcr.io/docling-project/docling-serve:main

README.md

@@ -1,431 +1,84 @@
+<p align="center">
+  <a href="https://github.com/docling-project/docling-serve">
+    <img loading="lazy" alt="Docling" src="https://github.com/docling-project/docling-serve/raw/main/docs/assets/docling-serve-pic.png" width="30%"/>
+  </a>
+</p>
+
 # Docling Serve
 
- Running [Docling](https://github.com/DS4SD/docling) as an API service.
+Running [Docling](https://github.com/docling-project/docling) as an API service.
 
-## Usage
+## Getting started
 
-The API provides two endpoints: one for urls, one for files. This is necessary to send files directly in binary format instead of base64-encoded strings.
+Install the `docling-serve` package and run the server.
 
-### Common parameters
+```bash
+# Using the python package
+pip install "docling-serve"
+docling-serve run
 
-On top of the source of file (see below), both endpoints support the same parameters, which are almost the same as the Docling CLI.
-
-- `from_format` (List[str]): Input format(s) to convert from. Allowed values: `docx`, `pptx`, `html`, `image`, `pdf`, `asciidoc`, `md`. Defaults to all formats.
-- `to_formats` (List[str]): Output format(s) to convert to. Allowed values: `md`, `json`, `html`, `text`, `doctags`. Defaults to `md`.
-- `do_ocr` (bool): If enabled, the bitmap content will be processed using OCR. Defaults to `True`.
-- `image_export_mode`: Image export mode for the document (only in case of JSON, Markdown or HTML). Allowed values: embedded, placeholder, referenced. Optional, defaults to `embedded`.
-- `force_ocr` (bool): If enabled, replace any existing text with OCR-generated text over the full content. Defaults to `False`.
-- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesseract_cli`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`.
-- `ocr_lang` (List[str]): List of languages used by the OCR engine. Note that each OCR engine has different values for the language names. Defaults to empty.
-- `pdf_backend` (str): PDF backend to use. Allowed values: `pypdfium2`, `dlparse_v1`, `dlparse_v2`. Defaults to `dlparse_v2`.
-- `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.
-- `do_table_structure` (bool): If enabled, the table structure will be extracted. Defaults to true.
-- `include_images` (bool): If enabled, images will be extracted from the document. Defaults to true.
-- `images_scale` (float): Scale factor for images. Defaults to 2.0.
-
-### URL endpoint
-
-The endpoint is `/v1alpha/convert/source`, listening for POST requests of JSON payloads.
-
-On top of the above parameters, you must send the URL(s) of the document you want process with either the `http_sources` or `file_sources` fields.
-The first is fetching URL(s) (optionally using with extra headers), the second allows to provide documents as base64-encoded strings.
-No `options` is required, they can be partially or completely omitted.
-
-Simple payload example:
-
-```json
-{
-  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
-}
+# Using container images, e.g. with Podman
+podman run -p 5001:5001 quay.io/docling-project/docling-serve
 ```
 
-<details>
+The server is available at
 
-<summary>Complete payload example:</summary>
+- API <http://127.0.0.1:5001>
+- API documentation <http://127.0.0.1:5001/docs>
+  ![swagger.png](img/swagger.png)
 
-```json
-{
-  "options": {
-    "from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
-    "to_formats": ["md", "json", "html", "text", "doctags"],
-    "image_export_mode": "placeholder",
-    "do_ocr": true,
-    "force_ocr": false,
-    "ocr_engine": "easyocr",
-    "ocr_lang": ["en"],
-    "pdf_backend": "dlparse_v2",
-    "table_mode": "fast",
-    "abort_on_error": false,
-    "return_as_file": false,
-  },
-  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
-}
-```
+Try it out with a simple conversion:
 
-</details>
-
-<details>
-
-<summary>CURL example:</summary>
-
-```sh
+```bash
 curl -X 'POST' \
   'http://localhost:5001/v1alpha/convert/source' \
   -H 'accept: application/json' \
   -H 'Content-Type: application/json' \
   -d '{
-  "options": {
-    "from_formats": [
-      "docx",
-      "pptx",
-      "html",
-      "image",
-      "pdf",
-      "asciidoc",
-      "md",
-      "xlsx"
-    ],
-    "to_formats": ["md", "json", "html", "text", "doctags"],
-    "image_export_mode": "placeholder",
-    "do_ocr": true,
-    "force_ocr": false,
-    "ocr_engine": "easyocr",
-    "ocr_lang": [
-      "fr",
-      "de",
-      "es",
-      "en"
-    ],
-    "pdf_backend": "dlparse_v2",
-    "table_mode": "fast",
-    "abort_on_error": false,
-    "return_as_file": false,
-    "do_table_structure": true,
-    "include_images": true,
-    "images_scale": 2
-  },
-  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
-}'
+    "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}]
+  }'
 ```
 
-</details>
+### Container images
 
-<details>
-<summary>Python example:</summary>
+Available container images:
 
-```python
-import httpx
+| Name | Description | Arch | Size |
+| -----|-------------|------|------|
+| [`ghcr.io/docling-project/docling-serve`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve) <br /> [`quay.io/docling-project/docling-serve`](https://quay.io/repository/docling-project/docling-serve) | Simple image for Docling Serve, installing all packages from the official pypi.org index. | `linux/amd64`, `linux/arm64` | 3.6 GB |
+| [`ghcr.io/docling-project/docling-serve-cpu`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cpu) <br /> [`quay.io/docling-project/docling-serve-cpu`](https://quay.io/repository/docling-project/docling-serve-cpu) | Cpu-only image which installs `torch` from the pytorch cpu index. | `linux/amd64`, `linux/arm64` | 3.6 GB |
+| [`ghcr.io/docling-project/docling-serve-cu124`](https://github.com/docling-project/docling-serve/pkgs/container/docling-serve-cu124) <br /> [`quay.io/docling-project/docling-serve-cu124`](https://quay.io/repository/docling-project/docling-serve-cu124) | Cuda 12.4 image which installs `torch` from the pytorch cu124 index. | `linux/amd64` | 8.7 GB |
 
-async_client = httpx.AsyncClient(timeout=60.0)
-url = "http://localhost:5001/v1alpha/convert/source"
-payload = {
-  "options": {
-    "from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
-    "to_formats": ["md", "json", "html", "text", "doctags"],
-    "image_export_mode": "placeholder",
-    "do_ocr": True,
-    "force_ocr": False,
-    "ocr_engine": "easyocr",
-    "ocr_lang": "en",
-    "pdf_backend": "dlparse_v2",
-    "table_mode": "fast",
-    "abort_on_error": False,
-    "return_as_file": False,
-  },
-  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
-}
+Coming soon: `docling-serve-slim` images will reduce the size by skipping the model weights download.
 
-response = await async_client_client.post(url, json=payload)
-
-data = response.json()
-```
-
-</details>
-
-#### File as base64
-
-The `file_sources` argument in the endpoint allows to send files as base64-encoded strings.
-When your PDF or other file type is too large, encoding it and passing it inline to curl
-can lead to an “Argument list too long” error on some systems. To avoid this, we write
-the JSON request body to a file and have curl read from that file.
-
-<details>
-<summary>CURL steps:</summary>
-
-```sh
-# 1. Base64-encode the file
-B64_DATA=$(base64 -w 0 /path/to/file/pdf-to-convert.pdf)
-
-# 2. Build the JSON with your options
-cat <<EOF > /tmp/request_body.json
-{
-  "options": {
-  },
-  "file_sources": [{
-    "base64_string": "${B64_DATA}",
-    "filename": "pdf-to-convert.pdf"
-  }]
-}
-EOF
-
-# 3. POST the request to the docling service
-curl -X POST "localhost:5001/v1alpha/convert/source" \
-     -H "Content-Type: application/json" \
-     -d @/tmp/request_body.json
-```
-
-</details>
-
-### File endpoint
-
-The endpoint is: `/v1alpha/convert/file`, listening for POST requests of Form payloads (necessary as the files are sent as multipart/form data). You can send one or multiple files.
-
-<details>
-<summary>CURL example:</summary>
-
-```sh
-curl -X 'POST' \
-  'http://127.0.0.1:5001/v1alpha/convert/file' \
-  -H 'accept: application/json' \
-  -H 'Content-Type: multipart/form-data' \
-  -F 'ocr_engine=easyocr' \
-  -F 'pdf_backend=dlparse_v2' \
-  -F 'from_formats=pdf' \
-  -F 'from_formats=docx' \
-  -F 'force_ocr=false' \
-  -F 'image_export_mode=embedded' \
-  -F 'ocr_lang=en' \
-  -F 'ocr_lang=pl' \
-  -F 'table_mode=fast' \
-  -F 'files=@2206.01062v1.pdf;type=application/pdf' \
-  -F 'abort_on_error=false' \
-  -F 'to_formats=md' \
-  -F 'to_formats=text' \
-  -F 'return_as_file=false' \
-  -F 'do_ocr=true'
-```
-
-</details>
-
-<details>
-<summary>Python example:</summary>
-
-```python
-import httpx
-
-async_client = httpx.AsyncClient(timeout=60.0)
-url = "http://localhost:5001/v1alpha/convert/file"
-parameters = {
-"from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
-"to_formats": ["md", "json", "html", "text", "doctags"],
-"image_export_mode": "placeholder",
-"do_ocr": True,
-"force_ocr": False,
-"ocr_engine": "easyocr",
-"ocr_lang": ["en"],
-"pdf_backend": "dlparse_v2",
-"table_mode": "fast",
-"abort_on_error": False,
-"return_as_file": False
-}
-
-current_dir = os.path.dirname(__file__)
-file_path = os.path.join(current_dir, '2206.01062v1.pdf')
-
-files = {
-    'files': ('2206.01062v1.pdf', open(file_path, 'rb'), 'application/pdf'),
-}
-
-response = await async_client.post(url, files=files, data={"parameters": json.dumps(parameters)})
-assert response.status_code == 200, "Response should be 200 OK"
-
-data = response.json()
-```
-
-</details>
-
-### Response format
-
-The response can be a JSON Document or a File.
-
-- If you process only one file, the response will be a JSON document with the following format:
-
-  ```jsonc
-  {
-    "document": {
-      "md_content": "",
-      "json_content": {},
-      "html_content": "",
-      "text_content": "",
-      "doctags_content": ""
-      },
-    "status": "<success|partial_success|skipped|failure>",
-    "processing_time": 0.0,
-    "timings": {},
-    "errors": []
-  }
-  ```
-
-  Depending on the value you set in `output_formats`, the different items will be populated with their respective results or empty.
-
-  `processing_time` is the Docling processing time in seconds, and `timings` (when enabled in the backend) provides the detailed
-  timing of all the internal Docling components.
-
-- If you set the parameter `return_as_file` to True, the response will be a zip file.
-- If multiple files are generated (multiple inputs, or one input but multiple outputs with `return_as_file` True), the response will be a zip file.
-
-## Run docling-serve
-
-Clone the repository and run the following from within the cloned directory root.
+### Demonstration UI
 
 ```bash
-python -m venv venv
-source venv/bin/activate
+# Install the Python package with the extra dependencies
 pip install "docling-serve[ui]"
 docling-serve run --enable-ui
+
+# Run the container image with the extra env parameters
+podman run -p 5001:5001 -e DOCLING_SERVE_ENABLE_UI=true quay.io/docling-project/docling-serve
 ```
 
-## Helpers
-
-- A full Swagger UI is available at the `/docs` endpoint.
-
-![swagger.png](img/swagger.png)
-
-- An easy to use UI is available at the `/ui` endpoint.
+An easy to use UI is available at the `/ui` endpoint.
 
 ![ui-input.png](img/ui-input.png)
 
 ![ui-output.png](img/ui-output.png)
 
-## Development
+## Documentation and advance usages
 
-### CPU only
-
-```sh
-# Install uv if not already available
-curl -LsSf https://astral.sh/uv/install.sh | sh
-
-# Install dependencies
-uv sync --extra cpu
-```
-
-### Cuda GPU
-
-For GPU support use the following command:
-
-```sh
-# Install dependencies
-uv sync
-```
-
-### Gradio UI and different OCR backends
-
-`/ui` endpoint using `gradio` and different OCR backends can be enabled via package extras:
-
-```sh
-# Enable ui and rapidocr
-uv sync --extra ui --extra rapidocr
-```
-
-```sh
-# Enable tesserocr
-uv sync --extra tesserocr
-```
-
-See `[project.optional-dependencies]` section in `pyproject.toml` for full list of options and runtime options with `uv run docling-serve --help`.
-
-### Run the server
-
-The `docling-serve` executable is a convenient script for launching the webserver both in
-development and production mode.
-
-```sh
-# Run the server in development mode
-# - reload is enabled by default
-# - listening on the 127.0.0.1 address
-# - ui is enabled by default
-docling-serve dev
-
-# Run the server in production mode
-# - reload is disabled by default
-# - listening on the 0.0.0.0 address
-# - ui is disabled by default
-docling-serve run
-```
-
-### Options
-
-The `docling-serve` executable allows is controlled with both command line
-options and environment variables.
-
-<details>
-<summary>`docling-serve` help message</summary>
-
-```sh
-$ docling-serve dev --help
-                                                                                                              
- Usage: docling-serve dev [OPTIONS]                                                                           
-                                                                                                              
- Run a Docling Serve app in development mode. 🧪                                                              
- This is equivalent to docling-serve run but with reload                                                      
- enabled and listening on the 127.0.0.1 address.                                                              
-                                                                                                              
- Options can be set also with the corresponding ENV variable, with the exception                              
- of --enable-ui, --host and --reload.                                                                         
-                                                                                                              
-╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ --host                                   TEXT     The host to serve on. For local development in localhost │
-│                                                   use 127.0.0.1. To enable public access, e.g. in a        │
-│                                                   container, use all the IP addresses available with       │
-│                                                   0.0.0.0.                                                 │
-│                                                   [default: 127.0.0.1]                                     │
-│ --port                                   INTEGER  The port to serve on. [default: 5001]                    │
-│ --reload           --no-reload                    Enable auto-reload of the server when (code) files       │
-│                                                   change. This is resource intensive, use it only during   │
-│                                                   development.                                             │
-│                                                   [default: reload]                                        │
-│ --root-path                              TEXT     The root path is used to tell your app that it is being  │
-│                                                   served to the outside world with some path prefix set up │
-│                                                   in some termination proxy or similar.                    │
-│ --proxy-headers    --no-proxy-headers             Enable/Disable X-Forwarded-Proto, X-Forwarded-For,       │
-│                                                   X-Forwarded-Port to populate remote address info.        │
-│                                                   [default: proxy-headers]                                 │
-│ --artifacts-path                          PATH     If set to a valid directory, the model weights will be  │
-│                                                    loaded from this path.                                  │
-│                                                    [default: None]                                         │
-│ --enable-ui        --no-enable-ui                 Enable the development UI. [default: enable-ui]          │
-│ --help                                            Show this message and exit.                              │
-╰────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
-```
-
-</details>
-
-#### Environment variables
-
-The environment variables controlling the `uvicorn` execution can be specified with the `UVICORN_` prefix:
-
-- `UVICORN_WORKERS`: Number of workers to use.
-- `UVICORN_RELOAD`: If `True`, this will enable auto-reload when you modify files, useful for development.
-
-The environment variables controlling specifics of the Docling Serve app can be specified with the
-`DOCLING_SERVE_` prefix:
-
-- `DOCLING_SERVE_ARTIFACTS_PATH`: if set Docling will use only the local weights of models, for example `/opt/app-root/src/.cache/docling/models`.
-- `DOCLING_SERVE_ENABLE_UI`: If `True`, The Gradio UI will be available at `/ui`.
-
-Others:
-
-- `TESSDATA_PREFIX`: Tesseract data location, example `/usr/share/tesseract/tessdata/`.
+Visit the [Docling Serve documentation](./docs/README.md) for learning how to [configure the webserver](./docs/configuration.md), use all the [runtime options](./docs/usage.md) of the API and [deployment examples](./docs/deployment.md).
 
 ## Get help and support
 
-Please feel free to connect with us using the [discussion section](https://github.com/DS4SD/docling/discussions).
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).
 
 ## Contributing
 
-Please read [Contributing to Docling Serve](https://github.com/DS4SD/docling-serve/blob/main/CONTRIBUTING.md) for details.
+Please read [Contributing to Docling Serve](https://github.com/docling-project/docling-serve/blob/main/CONTRIBUTING.md) for details.
 
 ## References
 
@@ -433,14 +86,14 @@ If you use Docling in your projects, please consider citing the following:
 
 ```bib
 @techreport{Docling,
-  author = {Deep Search Team},
-  month = {8},
-  title = {Docling Technical Report},
-  url = {https://arxiv.org/abs/2408.09869},
-  eprint = {2408.09869},
-  doi = {10.48550/arXiv.2408.09869},
-  version = {1.0.0},
-  year = {2024}
+  author = {Docling Contributors},
+  month = {1},
+  title = {Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion},
+  url = {https://arxiv.org/abs/2501.17887},
+  eprint = {2501.17887},
+  doi = {10.48550/arXiv.2501.17887},
+  version = {2.0.0},
+  year = {2025}
 }
 ```
 

docling_serve/__main__.py

@@ -74,12 +74,44 @@ def callback(
 def _run(
     *,
     command: str,
+    # Docling serve parameters
+    artifacts_path: Path | None,
+    enable_ui: bool,
 ) -> None:
     server_type = "development" if command == "dev" else "production"
 
     console.print(f"Starting {server_type} server 🚀")
 
-    url = f"http://{uvicorn_settings.host}:{uvicorn_settings.port}"
+    run_subprocess = (
+        uvicorn_settings.workers is not None and uvicorn_settings.workers > 1
+    ) or uvicorn_settings.reload
+
+    run_ssl = (
+        uvicorn_settings.ssl_certfile is not None
+        and uvicorn_settings.ssl_keyfile is not None
+    )
+
+    if run_subprocess and docling_serve_settings.artifacts_path != artifacts_path:
+        err_console.print(
+            "\n[yellow]:warning: The server will run with reload or multiple workers. \n"
+            "The argument [bold]--artifacts-path[/bold] will be ignored, please set the value \n"
+            "using the environment variable [bold]DOCLING_SERVE_ARTIFACTS_PATH[/bold].[/yellow]"
+        )
+
+    if run_subprocess and docling_serve_settings.enable_ui != enable_ui:
+        err_console.print(
+            "\n[yellow]:warning: The server will run with reload or multiple workers. \n"
+            "The argument [bold]--enable-ui[/bold] will be ignored, please set the value \n"
+            "using the environment variable [bold]DOCLING_SERVE_ENABLE_UI[/bold].[/yellow]"
+        )
+
+    # Propagate the settings to the app settings
+    docling_serve_settings.artifacts_path = artifacts_path
+    docling_serve_settings.enable_ui = enable_ui
+
+    # Print documentation
+    protocol = "https" if run_ssl else "http"
+    url = f"{protocol}://{uvicorn_settings.host}:{uvicorn_settings.port}"
     url_docs = f"{url}/docs"
     url_ui = f"{url}/ui"
 
@@ -99,6 +131,7 @@ def _run(
     console.print("")
     console.print("Logs:")
 
+    # Launch the server
     uvicorn.run(
         app="docling_serve.app:create_app",
         factory=True,
@@ -108,6 +141,10 @@ def _run(
         workers=uvicorn_settings.workers,
         root_path=uvicorn_settings.root_path,
         proxy_headers=uvicorn_settings.proxy_headers,
+        timeout_keep_alive=uvicorn_settings.timeout_keep_alive,
+        ssl_certfile=uvicorn_settings.ssl_certfile,
+        ssl_keyfile=uvicorn_settings.ssl_keyfile,
+        ssl_keyfile_password=uvicorn_settings.ssl_keyfile_password,
     )
 
 
@@ -159,6 +196,18 @@ def dev(
             )
         ),
     ] = uvicorn_settings.proxy_headers,
+    timeout_keep_alive: Annotated[
+        int, typer.Option(help="Timeout for the server response.")
+    ] = uvicorn_settings.timeout_keep_alive,
+    ssl_certfile: Annotated[
+        Optional[Path], typer.Option(help="SSL certificate file")
+    ] = uvicorn_settings.ssl_certfile,
+    ssl_keyfile: Annotated[
+        Optional[Path], typer.Option(help="SSL key file")
+    ] = uvicorn_settings.ssl_keyfile,
+    ssl_keyfile_password: Annotated[
+        Optional[str], typer.Option(help="SSL keyfile password")
+    ] = uvicorn_settings.ssl_keyfile_password,
     # docling options
     artifacts_path: Annotated[
         Optional[Path],
@@ -186,12 +235,15 @@ def dev(
     uvicorn_settings.reload = reload
     uvicorn_settings.root_path = root_path
     uvicorn_settings.proxy_headers = proxy_headers
-
-    docling_serve_settings.artifacts_path = artifacts_path
-    docling_serve_settings.enable_ui = enable_ui
+    uvicorn_settings.timeout_keep_alive = timeout_keep_alive
+    uvicorn_settings.ssl_certfile = ssl_certfile
+    uvicorn_settings.ssl_keyfile = ssl_keyfile
+    uvicorn_settings.ssl_keyfile_password = ssl_keyfile_password
 
     _run(
         command="dev",
+        artifacts_path=artifacts_path,
+        enable_ui=enable_ui,
     )
 
 
@@ -251,6 +303,18 @@ def run(
             )
         ),
     ] = uvicorn_settings.proxy_headers,
+    timeout_keep_alive: Annotated[
+        int, typer.Option(help="Timeout for the server response.")
+    ] = uvicorn_settings.timeout_keep_alive,
+    ssl_certfile: Annotated[
+        Optional[Path], typer.Option(help="SSL certificate file")
+    ] = uvicorn_settings.ssl_certfile,
+    ssl_keyfile: Annotated[
+        Optional[Path], typer.Option(help="SSL key file")
+    ] = uvicorn_settings.ssl_keyfile,
+    ssl_keyfile_password: Annotated[
+        Optional[str], typer.Option(help="SSL keyfile password")
+    ] = uvicorn_settings.ssl_keyfile_password,
     # docling options
     artifacts_path: Annotated[
         Optional[Path],
@@ -281,12 +345,15 @@ def run(
     uvicorn_settings.workers = workers
     uvicorn_settings.root_path = root_path
     uvicorn_settings.proxy_headers = proxy_headers
-
-    docling_serve_settings.artifacts_path = artifacts_path
-    docling_serve_settings.enable_ui = enable_ui
+    uvicorn_settings.timeout_keep_alive = timeout_keep_alive
+    uvicorn_settings.ssl_certfile = ssl_certfile
+    uvicorn_settings.ssl_keyfile = ssl_keyfile
+    uvicorn_settings.ssl_keyfile_password = ssl_keyfile_password
 
     _run(
         command="run",
+        artifacts_path=artifacts_path,
+        enable_ui=enable_ui,
     )
 
 

docling_serve/app.py

@@ -1,11 +1,11 @@
 import asyncio
 import importlib.metadata
 import logging
-import tempfile
+import shutil
+import time
 from contextlib import asynccontextmanager
 from io import BytesIO
-from pathlib import Path
-from typing import Annotated, Any, Optional, Union
+from typing import Annotated
 
 from fastapi import (
     BackgroundTasks,
@@ -18,14 +18,24 @@ from fastapi import (
     WebSocketDisconnect,
 )
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.openapi.docs import (
+    get_redoc_html,
+    get_swagger_ui_html,
+    get_swagger_ui_oauth2_redirect_html,
+)
 from fastapi.responses import RedirectResponse
+from fastapi.staticfiles import StaticFiles
 
-from docling.datamodel.base_models import DocumentStream, InputFormat
-from docling.document_converter import DocumentConverter
+from docling.datamodel.base_models import DocumentStream
 
+from docling_serve.datamodel.callback import (
+    ProgressCallbackRequest,
+    ProgressCallbackResponse,
+)
 from docling_serve.datamodel.convert import ConvertDocumentsOptions
 from docling_serve.datamodel.requests import (
     ConvertDocumentFileSourcesRequest,
+    ConvertDocumentHttpSourcesRequest,
     ConvertDocumentsRequest,
 )
 from docling_serve.datamodel.responses import (
@@ -35,19 +45,16 @@ from docling_serve.datamodel.responses import (
     TaskStatusResponse,
     WebsocketMessage,
 )
-from docling_serve.docling_conversion import (
-    convert_documents,
-    converters,
-    get_pdf_pipeline_opts,
-)
-from docling_serve.engines import get_orchestrator
-from docling_serve.engines.async_local.orchestrator import (
-    AsyncLocalOrchestrator,
-    TaskNotFoundError,
+from docling_serve.datamodel.task import Task, TaskSource
+from docling_serve.engines.async_orchestrator import (
+    BaseAsyncOrchestrator,
+    ProgressInvalid,
 )
+from docling_serve.engines.async_orchestrator_factory import get_async_orchestrator
+from docling_serve.engines.base_orchestrator import TaskNotFoundError
 from docling_serve.helper_functions import FormDepends
-from docling_serve.response_preparation import process_results
 from docling_serve.settings import docling_serve_settings
+from docling_serve.storage import get_scratch
 
 
 # Set up custom logging as we'll be intermixes with FastAPI/Uvicorn's logging
@@ -85,18 +92,11 @@ _log = logging.getLogger(__name__)
 # Context manager to initialize and clean up the lifespan of the FastAPI app
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    # Converter with default options
-    pdf_format_option, options_hash = get_pdf_pipeline_opts(ConvertDocumentsOptions())
-    converters[options_hash] = DocumentConverter(
-        format_options={
-            InputFormat.PDF: pdf_format_option,
-            InputFormat.IMAGE: pdf_format_option,
-        }
-    )
+    orchestrator = get_async_orchestrator()
+    scratch_dir = get_scratch()
 
-    converters[options_hash].initialize_pipeline(InputFormat.PDF)
-
-    orchestrator = get_orchestrator()
+    # Warm up processing cache
+    await orchestrator.warm_up_caches()
 
     # Start the background queue processor
     queue_task = asyncio.create_task(orchestrator.process_queue())
@@ -110,10 +110,9 @@ async def lifespan(app: FastAPI):
     except asyncio.CancelledError:
         _log.info("Queue processor cancelled.")
 
-    converters.clear()
-
-    # if WITH_UI:
-    #     gradio_ui.close()
+    # Remove scratch directory in case it was a tempfile
+    if docling_serve_settings.scratch_path is not None:
+        shutil.rmtree(scratch_dir, ignore_errors=True)
 
 
 ##################################
@@ -129,15 +128,25 @@ def create_app():  # noqa: C901
 
         version = "0.0.0"
 
+    offline_docs_assets = False
+    if (
+        docling_serve_settings.static_path is not None
+        and (docling_serve_settings.static_path).is_dir()
+    ):
+        offline_docs_assets = True
+        _log.info("Found static assets.")
+
     app = FastAPI(
         title="Docling Serve",
+        docs_url=None if offline_docs_assets else "/docs",
+        redoc_url=None if offline_docs_assets else "/redocs",
         lifespan=lifespan,
         version=version,
     )
 
-    origins = ["*"]
-    methods = ["*"]
-    headers = ["*"]
+    origins = docling_serve_settings.cors_origins
+    methods = docling_serve_settings.cors_methods
+    headers = docling_serve_settings.cors_headers
 
     app.add_middleware(
         CORSMiddleware,
@@ -154,7 +163,8 @@ def create_app():  # noqa: C901
 
             from docling_serve.gradio_ui import ui as gradio_ui
 
-            tmp_output_dir = Path(tempfile.mkdtemp())
+            tmp_output_dir = get_scratch() / "gradio"
+            tmp_output_dir.mkdir(exist_ok=True, parents=True)
             gradio_ui.gradio_output_dir = tmp_output_dir
             app = gr.mount_gradio_app(
                 app,
@@ -170,6 +180,88 @@ def create_app():  # noqa: C901
                 "or `pip install gradio`"
             )
 
+    #############################
+    # Offline assets definition #
+    #############################
+    if offline_docs_assets:
+        app.mount(
+            "/static",
+            StaticFiles(directory=docling_serve_settings.static_path),
+            name="static",
+        )
+
+        @app.get("/docs", include_in_schema=False)
+        async def custom_swagger_ui_html():
+            return get_swagger_ui_html(
+                openapi_url=app.openapi_url,
+                title=app.title + " - Swagger UI",
+                oauth2_redirect_url=app.swagger_ui_oauth2_redirect_url,
+                swagger_js_url="/static/swagger-ui-bundle.js",
+                swagger_css_url="/static/swagger-ui.css",
+            )
+
+        @app.get(app.swagger_ui_oauth2_redirect_url, include_in_schema=False)
+        async def swagger_ui_redirect():
+            return get_swagger_ui_oauth2_redirect_html()
+
+        @app.get("/redoc", include_in_schema=False)
+        async def redoc_html():
+            return get_redoc_html(
+                openapi_url=app.openapi_url,
+                title=app.title + " - ReDoc",
+                redoc_js_url="/static/redoc.standalone.js",
+            )
+
+    ########################
+    # Async / Sync helpers #
+    ########################
+
+    async def _enque_source(
+        orchestrator: BaseAsyncOrchestrator, conversion_request: ConvertDocumentsRequest
+    ) -> Task:
+        sources: list[TaskSource] = []
+        if isinstance(conversion_request, ConvertDocumentFileSourcesRequest):
+            sources.extend(conversion_request.file_sources)
+        if isinstance(conversion_request, ConvertDocumentHttpSourcesRequest):
+            sources.extend(conversion_request.http_sources)
+
+        task = await orchestrator.enqueue(
+            sources=sources, options=conversion_request.options
+        )
+        return task
+
+    async def _enque_file(
+        orchestrator: BaseAsyncOrchestrator,
+        files: list[UploadFile],
+        options: ConvertDocumentsOptions,
+    ) -> Task:
+        _log.info(f"Received {len(files)} files for processing.")
+
+        # Load the uploaded files to Docling DocumentStream
+        file_sources: list[TaskSource] = []
+        for i, file in enumerate(files):
+            buf = BytesIO(file.file.read())
+            suffix = "" if len(file_sources) == 1 else f"_{i}"
+            name = file.filename if file.filename else f"file{suffix}.pdf"
+            file_sources.append(DocumentStream(name=name, stream=buf))
+
+        task = await orchestrator.enqueue(sources=file_sources, options=options)
+        return task
+
+    async def _wait_task_complete(
+        orchestrator: BaseAsyncOrchestrator, task_id: str
+    ) -> bool:
+        MAX_WAIT = 120
+        start_time = time.monotonic()
+        while True:
+            task = await orchestrator.task_status(task_id=task_id)
+            if task.is_completed():
+                return True
+            await asyncio.sleep(5)
+            elapsed_time = time.monotonic() - start_time
+            if elapsed_time > MAX_WAIT:
+                return False
+
     #############################
     # API Endpoints definitions #
     #############################
@@ -177,9 +269,10 @@ def create_app():  # noqa: C901
     # Favicon
     @app.get("/favicon.ico", include_in_schema=False)
     async def favicon():
-        response = RedirectResponse(
-            url="https://ds4sd.github.io/docling/assets/logo.png"
-        )
+        logo_url = "https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"
+        if offline_docs_assets:
+            logo_url = "/static/logo.svg"
+        response = RedirectResponse(url=logo_url)
         return response
 
     @app.get("/health")
@@ -202,33 +295,33 @@ def create_app():  # noqa: C901
             }
         },
     )
-    def process_url(
-        background_tasks: BackgroundTasks, conversion_request: ConvertDocumentsRequest
+    async def process_url(
+        background_tasks: BackgroundTasks,
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
+        conversion_request: ConvertDocumentsRequest,
     ):
-        sources: list[Union[str, DocumentStream]] = []
-        headers: Optional[dict[str, Any]] = None
-        if isinstance(conversion_request, ConvertDocumentFileSourcesRequest):
-            for file_source in conversion_request.file_sources:
-                sources.append(file_source.to_document_stream())
-        else:
-            for http_source in conversion_request.http_sources:
-                sources.append(http_source.url)
-                if headers is None and http_source.headers:
-                    headers = http_source.headers
-
-        # Note: results are only an iterator->lazy evaluation
-        results = convert_documents(
-            sources=sources, options=conversion_request.options, headers=headers
+        task = await _enque_source(
+            orchestrator=orchestrator, conversion_request=conversion_request
+        )
+        success = await _wait_task_complete(
+            orchestrator=orchestrator, task_id=task.task_id
         )
 
-        # The real processing will happen here
-        response = process_results(
-            background_tasks=background_tasks,
-            conversion_options=conversion_request.options,
-            conv_results=results,
-        )
+        if not success:
+            # TODO: abort task!
+            return HTTPException(
+                status_code=504, detail="Conversion is taking too long."
+            )
 
-        return response
+        result = await orchestrator.task_result(
+            task_id=task.task_id, background_tasks=background_tasks
+        )
+        if result is None:
+            raise HTTPException(
+                status_code=404,
+                detail="Task result not found. Please wait for a completion status.",
+            )
+        return result
 
     # Convert a document from file(s)
     @app.post(
@@ -242,29 +335,34 @@ def create_app():  # noqa: C901
     )
     async def process_file(
         background_tasks: BackgroundTasks,
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
         files: list[UploadFile],
         options: Annotated[
             ConvertDocumentsOptions, FormDepends(ConvertDocumentsOptions)
         ],
     ):
-        _log.info(f"Received {len(files)} files for processing.")
-
-        # Load the uploaded files to Docling DocumentStream
-        file_sources = []
-        for file in files:
-            buf = BytesIO(file.file.read())
-            name = file.filename if file.filename else "file.pdf"
-            file_sources.append(DocumentStream(name=name, stream=buf))
-
-        results = convert_documents(sources=file_sources, options=options)
-
-        response = process_results(
-            background_tasks=background_tasks,
-            conversion_options=options,
-            conv_results=results,
+        task = await _enque_file(
+            orchestrator=orchestrator, files=files, options=options
+        )
+        success = await _wait_task_complete(
+            orchestrator=orchestrator, task_id=task.task_id
         )
 
-        return response
+        if not success:
+            # TODO: abort task!
+            return HTTPException(
+                status_code=504, detail="Conversion is taking too long."
+            )
+
+        result = await orchestrator.task_result(
+            task_id=task.task_id, background_tasks=background_tasks
+        )
+        if result is None:
+            raise HTTPException(
+                status_code=404,
+                detail="Task result not found. Please wait for a completion status.",
+            )
+        return result
 
     # Convert a document from URL(s) using the async api
     @app.post(
@@ -272,10 +370,12 @@ def create_app():  # noqa: C901
         response_model=TaskStatusResponse,
     )
     async def process_url_async(
-        orchestrator: Annotated[AsyncLocalOrchestrator, Depends(get_orchestrator)],
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
         conversion_request: ConvertDocumentsRequest,
     ):
-        task = await orchestrator.enqueue(request=conversion_request)
+        task = await _enque_source(
+            orchestrator=orchestrator, conversion_request=conversion_request
+        )
         task_queue_position = await orchestrator.get_queue_position(
             task_id=task.task_id
         )
@@ -283,6 +383,33 @@ def create_app():  # noqa: C901
             task_id=task.task_id,
             task_status=task.task_status,
             task_position=task_queue_position,
+            task_meta=task.processing_meta,
+        )
+
+    # Convert a document from file(s) using the async api
+    @app.post(
+        "/v1alpha/convert/file/async",
+        response_model=TaskStatusResponse,
+    )
+    async def process_file_async(
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
+        background_tasks: BackgroundTasks,
+        files: list[UploadFile],
+        options: Annotated[
+            ConvertDocumentsOptions, FormDepends(ConvertDocumentsOptions)
+        ],
+    ):
+        task = await _enque_file(
+            orchestrator=orchestrator, files=files, options=options
+        )
+        task_queue_position = await orchestrator.get_queue_position(
+            task_id=task.task_id
+        )
+        return TaskStatusResponse(
+            task_id=task.task_id,
+            task_status=task.task_status,
+            task_position=task_queue_position,
+            task_meta=task.processing_meta,
         )
 
     # Task status poll
@@ -291,7 +418,7 @@ def create_app():  # noqa: C901
         response_model=TaskStatusResponse,
     )
     async def task_status_poll(
-        orchestrator: Annotated[AsyncLocalOrchestrator, Depends(get_orchestrator)],
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
         task_id: str,
         wait: Annotated[
             float, Query(help="Number of seconds to wait for a completed status.")
@@ -306,6 +433,7 @@ def create_app():  # noqa: C901
             task_id=task.task_id,
             task_status=task.task_status,
             task_position=task_queue_position,
+            task_meta=task.processing_meta,
         )
 
     # Task status websocket
@@ -314,7 +442,7 @@ def create_app():  # noqa: C901
     )
     async def task_status_ws(
         websocket: WebSocket,
-        orchestrator: Annotated[AsyncLocalOrchestrator, Depends(get_orchestrator)],
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
         task_id: str,
     ):
         await websocket.accept()
@@ -339,6 +467,7 @@ def create_app():  # noqa: C901
                 task_id=task.task_id,
                 task_status=task.task_status,
                 task_position=task_queue_position,
+                task_meta=task.processing_meta,
             )
             await websocket.send_text(
                 WebsocketMessage(
@@ -353,6 +482,7 @@ def create_app():  # noqa: C901
                     task_id=task.task_id,
                     task_status=task.task_status,
                     task_position=task_queue_position,
+                    task_meta=task.processing_meta,
                 )
                 await websocket.send_text(
                     WebsocketMessage(
@@ -380,10 +510,13 @@ def create_app():  # noqa: C901
         },
     )
     async def task_result(
-        orchestrator: Annotated[AsyncLocalOrchestrator, Depends(get_orchestrator)],
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
+        background_tasks: BackgroundTasks,
         task_id: str,
     ):
-        result = await orchestrator.task_result(task_id=task_id)
+        result = await orchestrator.task_result(
+            task_id=task_id, background_tasks=background_tasks
+        )
         if result is None:
             raise HTTPException(
                 status_code=404,
@@ -391,4 +524,23 @@ def create_app():  # noqa: C901
             )
         return result
 
+    # Update task progress
+    @app.post(
+        "/v1alpha/callback/task/progress",
+        response_model=ProgressCallbackResponse,
+    )
+    async def callback_task_progress(
+        orchestrator: Annotated[BaseAsyncOrchestrator, Depends(get_async_orchestrator)],
+        request: ProgressCallbackRequest,
+    ):
+        try:
+            await orchestrator.receive_task_progress(request=request)
+            return ProgressCallbackResponse(status="ack")
+        except TaskNotFoundError:
+            raise HTTPException(status_code=404, detail="Task not found.")
+        except ProgressInvalid as err:
+            raise HTTPException(
+                status_code=400, detail=f"Invalid progress payload: {err}"
+            )
+
     return app

docling_serve/datamodel/callback.py

@@ -0,0 +1,50 @@
+import enum
+from typing import Annotated, Literal
+
+from pydantic import BaseModel, Field
+
+
+class ProgressKind(str, enum.Enum):
+    SET_NUM_DOCS = "set_num_docs"
+    UPDATE_PROCESSED = "update_processed"
+
+
+class BaseProgress(BaseModel):
+    kind: ProgressKind
+
+
+class ProgressSetNumDocs(BaseProgress):
+    kind: Literal[ProgressKind.SET_NUM_DOCS] = ProgressKind.SET_NUM_DOCS
+
+    num_docs: int
+
+
+class SucceededDocsItem(BaseModel):
+    source: str
+
+
+class FailedDocsItem(BaseModel):
+    source: str
+    error: str
+
+
+class ProgressUpdateProcessed(BaseProgress):
+    kind: Literal[ProgressKind.UPDATE_PROCESSED] = ProgressKind.UPDATE_PROCESSED
+
+    num_processed: int
+    num_succeeded: int
+    num_failed: int
+
+    docs_succeeded: list[SucceededDocsItem]
+    docs_failed: list[FailedDocsItem]
+
+
+class ProgressCallbackRequest(BaseModel):
+    task_id: str
+    progress: Annotated[
+        ProgressSetNumDocs | ProgressUpdateProcessed, Field(discriminator="kind")
+    ]
+
+
+class ProgressCallbackResponse(BaseModel):
+    status: Literal["ack"] = "ack"

docling_serve/datamodel/convert.py

@@ -1,12 +1,114 @@
 # Define the input options for the API
-from typing import Annotated, Optional
+from typing import Annotated, Any, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import AnyUrl, BaseModel, Field, model_validator
+from typing_extensions import Self
 
 from docling.datamodel.base_models import InputFormat, OutputFormat
-from docling.datamodel.pipeline_options import OcrEngine, PdfBackend, TableFormerMode
+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
 
+from docling_serve.settings import docling_serve_settings
+
+ocr_factory = get_ocr_factory(
+    allow_external_plugins=docling_serve_settings.allow_external_plugins
+)
+ocr_engines_enum = ocr_factory.get_enum()
+
+
+class PictureDescriptionLocal(BaseModel):
+    repo_id: Annotated[
+        str,
+        Field(
+            description="Repository id from the Hugging Face Hub.",
+            examples=[
+                "HuggingFaceTB/SmolVLM-256M-Instruct",
+                "ibm-granite/granite-vision-3.2-2b",
+            ],
+        ),
+    ]
+    prompt: Annotated[
+        str,
+        Field(
+            description="Prompt used when calling the vision-language model.",
+            examples=[
+                "Describe this image in a few sentences.",
+                "This is a figure from a document. Provide a detailed description of it.",
+            ],
+        ),
+    ] = "Describe this image in a few sentences."
+    generation_config: Annotated[
+        dict[str, Any],
+        Field(
+            description="Config from https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig",
+            examples=[{"max_new_tokens": 200, "do_sample": False}],
+        ),
+    ] = {"max_new_tokens": 200, "do_sample": False}
+
+
+class PictureDescriptionApi(BaseModel):
+    url: Annotated[
+        AnyUrl,
+        Field(
+            description="Endpoint which accepts openai-api compatible requests.",
+            examples=[
+                AnyUrl(
+                    "http://localhost:8000/v1/chat/completions"
+                ),  # example of a local vllm api
+                AnyUrl(
+                    "http://localhost:11434/v1/chat/completions"
+                ),  # example of ollama
+            ],
+        ),
+    ]
+    headers: Annotated[
+        dict[str, str],
+        Field(
+            description="Headers used for calling the API endpoint. For example, it could include authentication headers."
+        ),
+    ] = {}
+    params: Annotated[
+        dict[str, Any],
+        Field(
+            description="Model parameters.",
+            examples=[
+                {  # on vllm
+                    "model": "HuggingFaceTB/SmolVLM-256M-Instruct",
+                    "max_completion_tokens": 200,
+                },
+                {  # on vllm
+                    "model": "ibm-granite/granite-vision-3.2-2b",
+                    "max_completion_tokens": 200,
+                },
+                {  # on ollama
+                    "model": "granite3.2-vision:2b"
+                },
+            ],
+        ),
+    ] = {}
+    timeout: Annotated[float, Field(description="Timeout for the API request.")] = 20
+    prompt: Annotated[
+        str,
+        Field(
+            description="Prompt used when calling the vision-language model.",
+            examples=[
+                "Describe this image in a few sentences.",
+                "This is a figures from a document. Provide a detailed description of it.",
+            ],
+        ),
+    ] = "Describe this image in a few sentences."
+
 
 class ConvertDocumentsOptions(BaseModel):
     from_formats: Annotated[
@@ -69,18 +171,17 @@ class ConvertDocumentsOptions(BaseModel):
         ),
     ] = False
 
-    # TODO: use a restricted list based on what is installed on the system
-    ocr_engine: Annotated[
-        OcrEngine,
+    ocr_engine: Annotated[  # type: ignore
+        ocr_engines_enum,
         Field(
             description=(
                 "The OCR engine to use. String. "
-                "Allowed values: easyocr, tesseract, rapidocr. "
+                f"Allowed values: {', '.join([v.value for v in ocr_engines_enum])}. "
                 "Optional, defaults to easyocr."
             ),
-            examples=[OcrEngine.EASYOCR],
+            examples=[EasyOcrOptions.kind],
         ),
-    ] = OcrEngine.EASYOCR
+    ] = ocr_engines_enum(EasyOcrOptions.kind)  # type: ignore
 
     ocr_lang: Annotated[
         Optional[list[str]],
@@ -101,25 +202,46 @@ class ConvertDocumentsOptions(BaseModel):
             description=(
                 "The PDF backend to use. String. "
                 f"Allowed values: {', '.join([v.value for v in PdfBackend])}. "
-                f"Optional, defaults to {PdfBackend.DLPARSE_V2.value}."
+                f"Optional, defaults to {PdfBackend.DLPARSE_V4.value}."
             ),
-            examples=[PdfBackend.DLPARSE_V2],
+            examples=[PdfBackend.DLPARSE_V4],
         ),
-    ] = PdfBackend.DLPARSE_V2
+    ] = PdfBackend.DLPARSE_V4
 
     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,
@@ -172,3 +294,74 @@ class ConvertDocumentsOptions(BaseModel):
             examples=[2.0],
         ),
     ] = 2.0
+
+    do_code_enrichment: Annotated[
+        bool,
+        Field(
+            description=(
+                "If enabled, perform OCR code enrichment. "
+                "Boolean. Optional, defaults to false."
+            ),
+            examples=[False],
+        ),
+    ] = False
+
+    do_formula_enrichment: Annotated[
+        bool,
+        Field(
+            description=(
+                "If enabled, perform formula OCR, return LaTeX code. "
+                "Boolean. Optional, defaults to false."
+            ),
+            examples=[False],
+        ),
+    ] = False
+
+    do_picture_classification: Annotated[
+        bool,
+        Field(
+            description=(
+                "If enabled, classify pictures in documents. "
+                "Boolean. Optional, defaults to false."
+            ),
+            examples=[False],
+        ),
+    ] = False
+
+    do_picture_description: Annotated[
+        bool,
+        Field(
+            description=(
+                "If enabled, describe pictures in documents. "
+                "Boolean. Optional, defaults to false."
+            ),
+            examples=[False],
+        ),
+    ] = False
+
+    picture_description_local: Annotated[
+        Optional[PictureDescriptionLocal],
+        Field(
+            description="Options for running a local vision-language model in the picture description. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with picture_description_api."
+        ),
+    ] = None
+
+    picture_description_api: Annotated[
+        Optional[PictureDescriptionApi],
+        Field(
+            description="API details for using a vision-language model in the picture description. This parameter is mutually exclusive with picture_description_local."
+        ),
+    ] = None
+
+    @model_validator(mode="after")
+    def picture_description_exclusivity(self) -> Self:
+        # Validate picture description options
+        if (
+            self.picture_description_local is not None
+            and self.picture_description_api is not None
+        ):
+            raise ValueError(
+                "The parameters picture_description_local and picture_description_api are mutually exclusive, only one of them can be set."
+            )
+
+        return self

docling_serve/datamodel/engines.py

@@ -1,10 +1,4 @@
 import enum
-from typing import Optional
-
-from pydantic import BaseModel
-
-from docling_serve.datamodel.requests import ConvertDocumentsRequest
-from docling_serve.datamodel.responses import ConvertDocumentResponse
 
 
 class TaskStatus(str, enum.Enum):
@@ -16,15 +10,4 @@ class TaskStatus(str, enum.Enum):
 
 class AsyncEngine(str, enum.Enum):
     LOCAL = "local"
-
-
-class Task(BaseModel):
-    task_id: str
-    task_status: TaskStatus = TaskStatus.PENDING
-    request: Optional[ConvertDocumentsRequest]
-    result: Optional[ConvertDocumentResponse] = None
-
-    def is_completed(self) -> bool:
-        if self.task_status in [TaskStatus.SUCCESS, TaskStatus.FAILURE]:
-            return True
-        return False
+    KFP = "kfp"

docling_serve/datamodel/kfp.py

@@ -0,0 +1,7 @@
+from pydantic import AnyUrl, BaseModel
+
+
+class CallbackSpec(BaseModel):
+    url: AnyUrl
+    headers: dict[str, str] = {}
+    ca_cert: str = ""

docling_serve/datamodel/requests.py

@@ -2,7 +2,7 @@ import base64
 from io import BytesIO
 from typing import Annotated, Any, Union
 
-from pydantic import BaseModel, Field
+from pydantic import AnyHttpUrl, BaseModel, Field
 
 from docling.datamodel.base_models import DocumentStream
 
@@ -15,7 +15,7 @@ class DocumentsConvertBase(BaseModel):
 
 class HttpSource(BaseModel):
     url: Annotated[
-        str,
+        AnyHttpUrl,
         Field(
             description="HTTP url to process",
             examples=["https://arxiv.org/pdf/2206.01062"],

docling_serve/datamodel/responses.py

@@ -7,6 +7,8 @@ from docling.datamodel.document import ConversionStatus, ErrorItem
 from docling.utils.profiling import ProfilingItem
 from docling_core.types.doc import DoclingDocument
 
+from docling_serve.datamodel.task_meta import TaskProcessingMeta
+
 
 # Status
 class HealthCheckResponse(BaseModel):
@@ -38,6 +40,7 @@ class TaskStatusResponse(BaseModel):
     task_id: str
     task_status: str
     task_position: Optional[int] = None
+    task_meta: Optional[TaskProcessingMeta] = None
 
 
 class MessageKind(str, enum.Enum):

docling_serve/datamodel/task.py

@@ -0,0 +1,32 @@
+from pathlib import Path
+from typing import Optional, Union
+
+from fastapi.responses import FileResponse
+from pydantic import BaseModel, ConfigDict
+
+from docling.datamodel.base_models import DocumentStream
+
+from docling_serve.datamodel.convert import ConvertDocumentsOptions
+from docling_serve.datamodel.engines import TaskStatus
+from docling_serve.datamodel.requests import FileSource, HttpSource
+from docling_serve.datamodel.responses import ConvertDocumentResponse
+from docling_serve.datamodel.task_meta import TaskProcessingMeta
+
+TaskSource = Union[HttpSource, FileSource, DocumentStream]
+
+
+class Task(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    task_id: str
+    task_status: TaskStatus = TaskStatus.PENDING
+    sources: list[TaskSource] = []
+    options: Optional[ConvertDocumentsOptions]
+    result: Optional[Union[ConvertDocumentResponse, FileResponse]] = None
+    scratch_dir: Optional[Path] = None
+    processing_meta: Optional[TaskProcessingMeta] = None
+
+    def is_completed(self) -> bool:
+        if self.task_status in [TaskStatus.SUCCESS, TaskStatus.FAILURE]:
+            return True
+        return False

docling_serve/datamodel/task_meta.py

@@ -0,0 +1,8 @@
+from pydantic import BaseModel
+
+
+class TaskProcessingMeta(BaseModel):
+    num_docs: int
+    num_processed: int = 0
+    num_succeeded: int = 0
+    num_failed: int = 0

docling_serve/docling_conversion.py

@@ -1,7 +1,9 @@
 import hashlib
 import json
 import logging
+import sys
 from collections.abc import Iterable, Iterator
+from functools import lru_cache
 from pathlib import Path
 from typing import Any, Optional, Union
 
@@ -9,37 +11,37 @@ from fastapi import HTTPException
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import DocumentStream, InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
-    EasyOcrOptions,
-    OcrEngine,
     OcrOptions,
     PdfBackend,
+    PdfPipeline,
     PdfPipelineOptions,
-    RapidOcrOptions,
+    PictureDescriptionApiOptions,
+    PictureDescriptionVlmOptions,
     TableFormerMode,
-    TesseractOcrOptions,
+    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
+from docling_serve.datamodel.convert import ConvertDocumentsOptions, ocr_factory
 from docling_serve.helper_functions import _to_list_of_strings
 from docling_serve.settings import docling_serve_settings
 
 _log = logging.getLogger(__name__)
 
 
-# Document converters will be preloaded and stored in a dictionary
-converters: dict[bytes, DocumentConverter] = {}
-
-
 # Custom serializer for PdfFormatOption
 # (model_dump_json does not work with some classes)
-def _serialize_pdf_format_option(pdf_format_option: PdfFormatOption) -> str:
+def _hash_pdf_format_option(pdf_format_option: PdfFormatOption) -> bytes:
     data = pdf_format_option.model_dump()
 
     # pipeline_options are not fully serialized by model_dump, dedicated pass
@@ -64,51 +66,49 @@ def _serialize_pdf_format_option(pdf_format_option: PdfFormatOption) -> str:
         )
 
     # Serialize the dictionary to JSON with sorted keys to have consistent hashes
-    return json.dumps(data, sort_keys=True)
+    serialized_data = json.dumps(data, sort_keys=True)
+    options_hash = hashlib.sha1(serialized_data.encode()).digest()
+    return options_hash
 
 
-# Computes the PDF pipeline options and returns the PdfFormatOption and its hash
-def get_pdf_pipeline_opts(  # noqa: C901
-    request: ConvertDocumentsOptions,
-) -> tuple[PdfFormatOption, bytes]:
-    if request.ocr_engine == OcrEngine.EASYOCR:
-        try:
-            import easyocr  # noqa: F401
-        except ImportError:
-            raise HTTPException(
-                status_code=400,
-                detail="The requested OCR engine"
-                f" (ocr_engine={request.ocr_engine.value})"
-                " is not available on this system. Please choose another OCR engine "
-                "or contact your system administrator.",
-            )
-        ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=request.force_ocr)
-    elif request.ocr_engine == OcrEngine.TESSERACT:
-        try:
-            import tesserocr  # noqa: F401
-        except ImportError:
-            raise HTTPException(
-                status_code=400,
-                detail="The requested OCR engine"
-                f" (ocr_engine={request.ocr_engine.value})"
-                " is not available on this system. Please choose another OCR engine "
-                "or contact your system administrator.",
-            )
-        ocr_options = TesseractOcrOptions(force_full_page_ocr=request.force_ocr)
-    elif request.ocr_engine == OcrEngine.RAPIDOCR:
-        try:
-            from rapidocr_onnxruntime import RapidOCR  # noqa: F401
-        except ImportError:
-            raise HTTPException(
-                status_code=400,
-                detail="The requested OCR engine"
-                f" (ocr_engine={request.ocr_engine.value})"
-                " is not available on this system. Please choose another OCR engine "
-                "or contact your system administrator.",
-            )
-        ocr_options = RapidOcrOptions(force_full_page_ocr=request.force_ocr)
-    else:
-        raise RuntimeError(f"Unexpected OCR engine type {request.ocr_engine}")
+# Cache of DocumentConverter objects
+_options_map: dict[bytes, PdfFormatOption] = {}
+
+
+@lru_cache(maxsize=docling_serve_settings.options_cache_size)
+def _get_converter_from_hash(options_hash: bytes) -> DocumentConverter:
+    pdf_format_option = _options_map[options_hash]
+    format_options: dict[InputFormat, FormatOption] = {
+        InputFormat.PDF: pdf_format_option,
+        InputFormat.IMAGE: pdf_format_option,
+    }
+
+    return DocumentConverter(format_options=format_options)
+
+
+def get_converter(pdf_format_option: PdfFormatOption) -> DocumentConverter:
+    options_hash = _hash_pdf_format_option(pdf_format_option)
+    _options_map[options_hash] = pdf_format_option
+    return _get_converter_from_hash(options_hash)
+
+
+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
+            force_full_page_ocr=request.force_ocr,
+        )
+    except ImportError as err:
+        raise HTTPException(
+            status_code=400,
+            detail="The requested OCR engine"
+            f" (ocr_engine={request.ocr_engine.value})"  # type: ignore
+            " is not available on this system. Please choose another OCR engine "
+            "or contact your system administrator.\n"
+            f"{err}",
+        )
 
     if request.ocr_lang is not None:
         if isinstance(request.ocr_lang, str):
@@ -117,62 +117,129 @@ def get_pdf_pipeline_opts(  # noqa: C901
             ocr_options.lang = request.ocr_lang
 
     pipeline_options = PdfPipelineOptions(
+        artifacts_path=artifacts_path,
+        enable_remote_services=docling_serve_settings.enable_remote_services,
+        document_timeout=request.document_timeout,
         do_ocr=request.do_ocr,
         ocr_options=ocr_options,
         do_table_structure=request.do_table_structure,
+        do_code_enrichment=request.do_code_enrichment,
+        do_formula_enrichment=request.do_formula_enrichment,
+        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:
         pipeline_options.generate_page_images = True
+        if request.image_export_mode == ImageRefMode.REFERENCED:
+            pipeline_options.generate_picture_images = True
         if request.images_scale:
             pipeline_options.images_scale = request.images_scale
 
+    if request.picture_description_local is not None:
+        pipeline_options.picture_description_options = (
+            PictureDescriptionVlmOptions.model_validate(
+                request.picture_description_local.model_dump()
+            )
+        )
+
+    if request.picture_description_api is not None:
+        pipeline_options.picture_description_options = (
+            PictureDescriptionApiOptions.model_validate(
+                request.picture_description_api.model_dump()
+            )
+        )
+
+    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:
         backend = DoclingParseV2DocumentBackend
+    elif request.pdf_backend == PdfBackend.DLPARSE_V4:
+        backend = DoclingParseV4DocumentBackend
     elif request.pdf_backend == PdfBackend.PYPDFIUM2:
         backend = PyPdfiumDocumentBackend
     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 "
+                "artifacts_path is an empty path, model weights will be downloaded "
                 "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,
+        )
 
-    serialized_data = _serialize_pdf_format_option(pdf_format_option)
+    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."
+        )
 
-    options_hash = hashlib.sha1(serialized_data.encode()).digest()
-
-    return pdf_format_option, options_hash
+    return pdf_format_option
 
 
 def convert_documents(
@@ -180,20 +247,14 @@ def convert_documents(
     options: ConvertDocumentsOptions,
     headers: Optional[dict[str, Any]] = None,
 ):
-    pdf_format_option, options_hash = get_pdf_pipeline_opts(options)
-
-    if options_hash not in converters:
-        format_options: dict[InputFormat, FormatOption] = {
-            InputFormat.PDF: pdf_format_option,
-            InputFormat.IMAGE: pdf_format_option,
-        }
-
-        converters[options_hash] = DocumentConverter(format_options=format_options)
-        _log.info(f"We now have {len(converters)} converters in memory.")
-
-    results: Iterator[ConversionResult] = converters[options_hash].convert_all(
+    pdf_format_option = get_pdf_pipeline_opts(options)
+    converter = get_converter(pdf_format_option)
+    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

docling_serve/engines/__init__.py

@@ -1,8 +0,0 @@
-from functools import lru_cache
-
-from docling_serve.engines.async_local.orchestrator import AsyncLocalOrchestrator
-
-
-@lru_cache
-def get_orchestrator() -> AsyncLocalOrchestrator:
-    return AsyncLocalOrchestrator()

docling_serve/engines/async_kfp/kfp_pipeline.py

@@ -0,0 +1,137 @@
+# ruff: noqa: E402, UP006, UP035
+
+from typing import Any, Dict, List
+
+from kfp import dsl
+
+PYTHON_BASE_IMAGE = "python:3.12"
+
+
+@dsl.component(
+    base_image=PYTHON_BASE_IMAGE,
+    packages_to_install=[
+        "pydantic",
+        "docling-serve @ git+https://github.com/docling-project/docling-serve@feat-kfp-engine",
+    ],
+    pip_index_urls=["https://download.pytorch.org/whl/cpu", "https://pypi.org/simple"],
+)
+def generate_chunks(
+    run_name: str,
+    request: Dict[str, Any],
+    batch_size: int,
+    callbacks: List[Dict[str, Any]],
+) -> List[List[Dict[str, Any]]]:
+    from pydantic import TypeAdapter
+
+    from docling_serve.datamodel.callback import (
+        ProgressCallbackRequest,
+        ProgressSetNumDocs,
+    )
+    from docling_serve.datamodel.kfp import CallbackSpec
+    from docling_serve.engines.async_kfp.notify import notify_callbacks
+
+    CallbacksListType = TypeAdapter(list[CallbackSpec])
+
+    sources = request["http_sources"]
+    splits = [sources[i : i + batch_size] for i in range(0, len(sources), batch_size)]
+
+    total = sum(len(chunk) for chunk in splits)
+    payload = ProgressCallbackRequest(
+        task_id=run_name, progress=ProgressSetNumDocs(num_docs=total)
+    )
+    notify_callbacks(
+        payload=payload,
+        callbacks=CallbacksListType.validate_python(callbacks),
+    )
+
+    return splits
+
+
+@dsl.component(
+    base_image=PYTHON_BASE_IMAGE,
+    packages_to_install=[
+        "pydantic",
+        "docling-serve @ git+https://github.com/docling-project/docling-serve@feat-kfp-engine",
+    ],
+    pip_index_urls=["https://download.pytorch.org/whl/cpu", "https://pypi.org/simple"],
+)
+def convert_batch(
+    run_name: str,
+    data_splits: List[Dict[str, Any]],
+    request: Dict[str, Any],
+    callbacks: List[Dict[str, Any]],
+    output_path: dsl.OutputPath("Directory"),  # type: ignore
+):
+    from pathlib import Path
+
+    from pydantic import AnyUrl, TypeAdapter
+
+    from docling_serve.datamodel.callback import (
+        FailedDocsItem,
+        ProgressCallbackRequest,
+        ProgressUpdateProcessed,
+        SucceededDocsItem,
+    )
+    from docling_serve.datamodel.convert import ConvertDocumentsOptions
+    from docling_serve.datamodel.kfp import CallbackSpec
+    from docling_serve.datamodel.requests import HttpSource
+    from docling_serve.engines.async_kfp.notify import notify_callbacks
+
+    CallbacksListType = TypeAdapter(list[CallbackSpec])
+
+    convert_options = ConvertDocumentsOptions.model_validate(request["options"])
+    print(convert_options)
+
+    output_dir = Path(output_path)
+    output_dir.mkdir(exist_ok=True, parents=True)
+    docs_succeeded: list[SucceededDocsItem] = []
+    docs_failed: list[FailedDocsItem] = []
+    for source_dict in data_splits:
+        source = HttpSource.model_validate(source_dict)
+        filename = Path(str(AnyUrl(source.url).path)).name
+        output_filename = output_dir / filename
+        print(f"Writing {output_filename}")
+        with output_filename.open("w") as f:
+            f.write(source.model_dump_json())
+        docs_succeeded.append(SucceededDocsItem(source=source.url))
+
+    payload = ProgressCallbackRequest(
+        task_id=run_name,
+        progress=ProgressUpdateProcessed(
+            num_failed=len(docs_failed),
+            num_processed=len(docs_succeeded) + len(docs_failed),
+            num_succeeded=len(docs_succeeded),
+            docs_succeeded=docs_succeeded,
+            docs_failed=docs_failed,
+        ),
+    )
+
+    print(payload)
+    notify_callbacks(
+        payload=payload,
+        callbacks=CallbacksListType.validate_python(callbacks),
+    )
+
+
+@dsl.pipeline()
+def process(
+    batch_size: int,
+    request: Dict[str, Any],
+    callbacks: List[Dict[str, Any]] = [],
+    run_name: str = "",
+):
+    chunks_task = generate_chunks(
+        run_name=run_name,
+        request=request,
+        batch_size=batch_size,
+        callbacks=callbacks,
+    )
+    chunks_task.set_caching_options(False)
+
+    with dsl.ParallelFor(chunks_task.output, parallelism=4) as data_splits:
+        convert_batch(
+            run_name=run_name,
+            data_splits=data_splits,
+            request=request,
+            callbacks=callbacks,
+        )

docling_serve/engines/async_kfp/notify.py

@@ -0,0 +1,32 @@
+import ssl
+
+import certifi
+import httpx
+
+from docling_serve.datamodel.callback import ProgressCallbackRequest
+from docling_serve.datamodel.kfp import CallbackSpec
+
+
+def notify_callbacks(
+    payload: ProgressCallbackRequest,
+    callbacks: list[CallbackSpec],
+):
+    if len(callbacks) == 0:
+        return
+
+    for callback in callbacks:
+        # https://www.python-httpx.org/advanced/ssl/#configuring-client-instances
+        if callback.ca_cert:
+            ctx = ssl.create_default_context(cadata=callback.ca_cert)
+        else:
+            ctx = ssl.create_default_context(cafile=certifi.where())
+
+        try:
+            httpx.post(
+                str(callback.url),
+                headers=callback.headers,
+                json=payload.model_dump(mode="json"),
+                verify=ctx,
+            )
+        except httpx.HTTPError as err:
+            print(f"Error notifying callback {callback.url}: {err}")

docling_serve/engines/async_kfp/orchestrator.py

@@ -0,0 +1,235 @@
+import datetime
+import json
+import logging
+import uuid
+from pathlib import Path
+from typing import Optional
+
+from kfp_server_api.models import V2beta1RuntimeState
+from pydantic import BaseModel, TypeAdapter
+from pydantic_settings import SettingsConfigDict
+
+from docling_serve.datamodel.callback import (
+    ProgressCallbackRequest,
+    ProgressSetNumDocs,
+    ProgressUpdateProcessed,
+)
+from docling_serve.datamodel.convert import ConvertDocumentsOptions
+from docling_serve.datamodel.engines import TaskStatus
+from docling_serve.datamodel.kfp import CallbackSpec
+from docling_serve.datamodel.requests import HttpSource
+from docling_serve.datamodel.task import Task, TaskSource
+from docling_serve.datamodel.task_meta import TaskProcessingMeta
+from docling_serve.engines.async_kfp.kfp_pipeline import process
+from docling_serve.engines.async_orchestrator import (
+    BaseAsyncOrchestrator,
+    ProgressInvalid,
+)
+from docling_serve.settings import docling_serve_settings
+
+_log = logging.getLogger(__name__)
+
+
+class _RunItem(BaseModel):
+    model_config = SettingsConfigDict(arbitrary_types_allowed=True)
+
+    run_id: str
+    state: str
+    created_at: datetime.datetime
+    scheduled_at: datetime.datetime
+    finished_at: datetime.datetime
+
+
+class AsyncKfpOrchestrator(BaseAsyncOrchestrator):
+    def __init__(self):
+        super().__init__()
+        import kfp
+
+        kfp_endpoint = docling_serve_settings.eng_kfp_endpoint
+        if kfp_endpoint is None:
+            raise ValueError("KFP endpoint is required when using the KFP engine.")
+
+        kube_sa_token_path = Path("/run/secrets/kubernetes.io/serviceaccount/token")
+        kube_sa_ca_cert_path = Path(
+            "/run/secrets/kubernetes.io/serviceaccount/service-ca.crt"
+        )
+
+        ssl_ca_cert = docling_serve_settings.eng_kfp_ca_cert_path
+        token = docling_serve_settings.eng_kfp_token
+        if (
+            ssl_ca_cert is None
+            and ".svc" in kfp_endpoint.host
+            and kube_sa_ca_cert_path.exists()
+        ):
+            ssl_ca_cert = str(kube_sa_ca_cert_path)
+        if token is None and kube_sa_token_path.exists():
+            token = kube_sa_token_path.read_text()
+
+        self._client = kfp.Client(
+            host=str(kfp_endpoint),
+            existing_token=token,
+            ssl_ca_cert=ssl_ca_cert,
+            # verify_ssl=False,
+        )
+
+    async def enqueue(
+        self, sources: list[TaskSource], options: ConvertDocumentsOptions
+    ) -> Task:
+        callbacks = []
+        if docling_serve_settings.eng_kfp_self_callback_endpoint is not None:
+            headers = {}
+            if docling_serve_settings.eng_kfp_self_callback_token_path is not None:
+                token = (
+                    docling_serve_settings.eng_kfp_self_callback_token_path.read_text()
+                )
+                headers["Authorization"] = f"Bearer {token}"
+            ca_cert = ""
+            if docling_serve_settings.eng_kfp_self_callback_ca_cert_path is not None:
+                ca_cert = docling_serve_settings.eng_kfp_self_callback_ca_cert_path.read_text()
+            callbacks.append(
+                CallbackSpec(
+                    url=docling_serve_settings.eng_kfp_self_callback_endpoint,
+                    headers=headers,
+                    ca_cert=ca_cert,
+                )
+            )
+
+        CallbacksType = TypeAdapter(list[CallbackSpec])
+        SourcesListType = TypeAdapter(list[HttpSource])
+        http_sources = [s for s in sources if isinstance(s, HttpSource)]
+        # hack: since the current kfp backend is not resolving the job_id placeholder,
+        # we set the run_name and pass it as argument to the job itself.
+        run_name = f"docling-job-{uuid.uuid4()}"
+        kfp_run = self._client.create_run_from_pipeline_func(
+            process,
+            arguments={
+                "batch_size": 10,
+                "sources": SourcesListType.dump_python(http_sources, mode="json"),
+                "options": options.model_dump(mode="json"),
+                "callbacks": CallbacksType.dump_python(callbacks, mode="json"),
+                "run_name": run_name,
+            },
+            run_name=run_name,
+        )
+        task_id = kfp_run.run_id
+
+        task = Task(task_id=task_id, sources=sources, options=options)
+        await self.init_task_tracking(task)
+        return task
+
+    async def _update_task_from_run(self, task_id: str, wait: float = 0.0):
+        run_info = self._client.get_run(run_id=task_id)
+        task = await self.get_raw_task(task_id=task_id)
+        # RUNTIME_STATE_UNSPECIFIED = "RUNTIME_STATE_UNSPECIFIED"
+        # PENDING = "PENDING"
+        # RUNNING = "RUNNING"
+        # SUCCEEDED = "SUCCEEDED"
+        # SKIPPED = "SKIPPED"
+        # FAILED = "FAILED"
+        # CANCELING = "CANCELING"
+        # CANCELED = "CANCELED"
+        # PAUSED = "PAUSED"
+        if run_info.state == V2beta1RuntimeState.SUCCEEDED:
+            task.task_status = TaskStatus.SUCCESS
+        elif run_info.state == V2beta1RuntimeState.PENDING:
+            task.task_status = TaskStatus.PENDING
+        elif run_info.state == V2beta1RuntimeState.RUNNING:
+            task.task_status = TaskStatus.STARTED
+        else:
+            task.task_status = TaskStatus.FAILURE
+
+    async def task_status(self, task_id: str, wait: float = 0.0) -> Task:
+        await self._update_task_from_run(task_id=task_id, wait=wait)
+        return await self.get_raw_task(task_id=task_id)
+
+    async def _get_pending(self) -> list[_RunItem]:
+        runs: list[_RunItem] = []
+        next_page: Optional[str] = None
+        while True:
+            res = self._client.list_runs(
+                page_token=next_page,
+                page_size=20,
+                filter=json.dumps(
+                    {
+                        "predicates": [
+                            {
+                                "operation": "EQUALS",
+                                "key": "state",
+                                "stringValue": "PENDING",
+                            }
+                        ]
+                    }
+                ),
+            )
+            if res.runs is not None:
+                for run in res.runs:
+                    runs.append(
+                        _RunItem(
+                            run_id=run.run_id,
+                            state=run.state,
+                            created_at=run.created_at,
+                            scheduled_at=run.scheduled_at,
+                            finished_at=run.finished_at,
+                        )
+                    )
+            if res.next_page_token is None:
+                break
+            next_page = res.next_page_token
+        return runs
+
+    async def queue_size(self) -> int:
+        runs = await self._get_pending()
+        return len(runs)
+
+    async def get_queue_position(self, task_id: str) -> Optional[int]:
+        runs = await self._get_pending()
+        for pos, run in enumerate(runs, start=1):
+            if run.run_id == task_id:
+                return pos
+        return None
+
+    async def process_queue(self):
+        return
+
+    async def warm_up_caches(self):
+        return
+
+    async def _get_run_id(self, run_name: str) -> str:
+        res = self._client.list_runs(
+            filter=json.dumps(
+                {
+                    "predicates": [
+                        {
+                            "operation": "EQUALS",
+                            "key": "name",
+                            "stringValue": run_name,
+                        }
+                    ]
+                }
+            ),
+        )
+        if res.runs is not None and len(res.runs) > 0:
+            return res.runs[0].run_id
+        raise RuntimeError(f"Run with {run_name=} not found.")
+
+    async def receive_task_progress(self, request: ProgressCallbackRequest):
+        task_id = await self._get_run_id(run_name=request.task_id)
+        progress = request.progress
+        task = await self.get_raw_task(task_id=task_id)
+
+        if isinstance(progress, ProgressSetNumDocs):
+            task.processing_meta = TaskProcessingMeta(num_docs=progress.num_docs)
+            task.task_status = TaskStatus.STARTED
+
+        elif isinstance(progress, ProgressUpdateProcessed):
+            if task.processing_meta is None:
+                raise ProgressInvalid(
+                    "UpdateProcessed was called before setting the expected number of documents."
+                )
+            task.processing_meta.num_processed += progress.num_processed
+            task.processing_meta.num_succeeded += progress.num_succeeded
+            task.processing_meta.num_failed += progress.num_failed
+            task.task_status = TaskStatus.STARTED
+
+        # TODO: could be moved to BackgroundTask
+        await self.notify_task_subscribers(task_id=task_id)

docling_serve/engines/async_local/orchestrator.py

@@ -3,43 +3,30 @@ import logging
 import uuid
 from typing import Optional
 
-from fastapi import WebSocket
-
-from docling_serve.datamodel.engines import Task, TaskStatus
-from docling_serve.datamodel.requests import ConvertDocumentsRequest
-from docling_serve.datamodel.responses import (
-    MessageKind,
-    TaskStatusResponse,
-    WebsocketMessage,
-)
+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
 from docling_serve.engines.async_local.worker import AsyncLocalWorker
-from docling_serve.engines.base_orchestrator import BaseOrchestrator
+from docling_serve.engines.async_orchestrator import BaseAsyncOrchestrator
 from docling_serve.settings import docling_serve_settings
 
 _log = logging.getLogger(__name__)
 
 
-class OrchestratorError(Exception):
-    pass
-
-
-class TaskNotFoundError(OrchestratorError):
-    pass
-
-
-class AsyncLocalOrchestrator(BaseOrchestrator):
+class AsyncLocalOrchestrator(BaseAsyncOrchestrator):
     def __init__(self):
+        super().__init__()
         self.task_queue = asyncio.Queue()
-        self.tasks: dict[str, Task] = {}
         self.queue_list: list[str] = []
-        self.task_subscribers: dict[str, set[WebSocket]] = {}
 
-    async def enqueue(self, request: ConvertDocumentsRequest) -> Task:
+    async def enqueue(
+        self, sources: list[TaskSource], options: ConvertDocumentsOptions
+    ) -> Task:
         task_id = str(uuid.uuid4())
-        task = Task(task_id=task_id, request=request)
-        self.tasks[task_id] = task
+        task = Task(task_id=task_id, sources=sources, options=options)
+        await self.init_task_tracking(task)
+
         self.queue_list.append(task_id)
-        self.task_subscribers[task_id] = set()
         await self.task_queue.put(task_id)
         return task
 
@@ -51,16 +38,6 @@ class AsyncLocalOrchestrator(BaseOrchestrator):
             self.queue_list.index(task_id) + 1 if task_id in self.queue_list else None
         )
 
-    async def task_status(self, task_id: str, wait: float = 0.0) -> Task:
-        if task_id not in self.tasks:
-            raise TaskNotFoundError()
-        return self.tasks[task_id]
-
-    async def task_result(self, task_id: str):
-        if task_id not in self.tasks:
-            raise TaskNotFoundError()
-        return self.tasks[task_id].result
-
     async def process_queue(self):
         # Create a pool of workers
         workers = []
@@ -74,28 +51,7 @@ class AsyncLocalOrchestrator(BaseOrchestrator):
         await asyncio.gather(*workers)
         _log.debug("All workers completed.")
 
-    async def notify_task_subscribers(self, task_id: str):
-        if task_id not in self.task_subscribers:
-            raise RuntimeError(f"Task {task_id} does not have a subscribers list.")
-
-        task = self.tasks[task_id]
-        task_queue_position = await self.get_queue_position(task_id)
-        msg = TaskStatusResponse(
-            task_id=task.task_id,
-            task_status=task.task_status,
-            task_position=task_queue_position,
-        )
-        for websocket in self.task_subscribers[task_id]:
-            await websocket.send_text(
-                WebsocketMessage(message=MessageKind.UPDATE, task=msg).model_dump_json()
-            )
-            if task.is_completed():
-                await websocket.close()
-
-    async def notify_queue_positions(self):
-        for task_id in self.task_subscribers.keys():
-            # notify only pending tasks
-            if self.tasks[task_id].task_status != TaskStatus.PENDING:
-                continue
-
-            await self.notify_task_subscribers(task_id)
+    async def warm_up_caches(self):
+        # Converter with default options
+        pdf_format_option = get_pdf_pipeline_opts(ConvertDocumentsOptions())
+        get_converter(pdf_format_option)

docling_serve/engines/async_local/worker.py

@@ -1,17 +1,18 @@
 import asyncio
 import logging
+import shutil
 import time
 from typing import TYPE_CHECKING, Any, Optional, Union
 
-from fastapi import BackgroundTasks
+from fastapi.responses import FileResponse
 
 from docling.datamodel.base_models import DocumentStream
 
 from docling_serve.datamodel.engines import TaskStatus
-from docling_serve.datamodel.requests import ConvertDocumentFileSourcesRequest
-from docling_serve.datamodel.responses import ConvertDocumentResponse
+from docling_serve.datamodel.requests import FileSource, HttpSource
 from docling_serve.docling_conversion import convert_documents
 from docling_serve.response_preparation import process_results
+from docling_serve.storage import get_scratch
 
 if TYPE_CHECKING:
     from docling_serve.engines.async_local.orchestrator import AsyncLocalOrchestrator
@@ -44,59 +45,66 @@ class AsyncLocalWorker:
                 # Notify clients about queue updates
                 await self.orchestrator.notify_queue_positions()
 
-                # Get the current event loop
-                asyncio.get_event_loop()
-
                 # Define a callback function to send progress updates to the client.
                 # TODO: send partial updates, e.g. when a document in the batch is done
                 def run_conversion():
-                    sources: list[Union[str, DocumentStream]] = []
+                    convert_sources: list[Union[str, DocumentStream]] = []
                     headers: Optional[dict[str, Any]] = None
-                    if isinstance(task.request, ConvertDocumentFileSourcesRequest):
-                        for file_source in task.request.file_sources:
-                            sources.append(file_source.to_document_stream())
-                    else:
-                        for http_source in task.request.http_sources:
-                            sources.append(http_source.url)
-                            if headers is None and http_source.headers:
-                                headers = http_source.headers
+                    for source in task.sources:
+                        if isinstance(source, DocumentStream):
+                            convert_sources.append(source)
+                        elif isinstance(source, FileSource):
+                            convert_sources.append(source.to_document_stream())
+                        elif isinstance(source, HttpSource):
+                            convert_sources.append(str(source.url))
+                            if headers is None and source.headers:
+                                headers = source.headers
 
                     # Note: results are only an iterator->lazy evaluation
                     results = convert_documents(
-                        sources=sources,
-                        options=task.request.options,
+                        sources=convert_sources,
+                        options=task.options,
                         headers=headers,
                     )
 
                     # The real processing will happen here
+                    work_dir = get_scratch() / task_id
                     response = process_results(
-                        background_tasks=BackgroundTasks(),
-                        conversion_options=task.request.options,
+                        conversion_options=task.options,
                         conv_results=results,
+                        work_dir=work_dir,
                     )
 
+                    if work_dir.exists():
+                        task.scratch_dir = work_dir
+                        if not isinstance(response, FileResponse):
+                            _log.warning(
+                                f"Task {task_id=} produced content in {work_dir=} but the response is not a file."
+                            )
+                            shutil.rmtree(work_dir, ignore_errors=True)
+
                     return response
 
-                # Run the prediction in a thread to avoid blocking the event loop.
                 start_time = time.monotonic()
+
+                # Run the prediction in a thread to avoid blocking the event loop.
+                # Get the current event loop
+                # loop = asyncio.get_event_loop()
                 # future = asyncio.run_coroutine_threadsafe(
                 #     run_conversion(),
                 #     loop=loop
                 # )
                 # response = future.result()
 
+                # Run in a thread
                 response = await asyncio.to_thread(
                     run_conversion,
                 )
                 processing_time = time.monotonic() - start_time
 
-                if not isinstance(response, ConvertDocumentResponse):
-                    _log.error(
-                        f"Worker {self.worker_id} got un-processable "
-                        "result for {task_id}: {type(response)}"
-                    )
                 task.result = response
-                task.request = None
+                task.sources = []
+                task.options = None
 
                 task.task_status = TaskStatus.SUCCESS
                 _log.info(

docling_serve/engines/async_orchestrator.py

@@ -0,0 +1,85 @@
+import shutil
+from typing import Union
+
+from fastapi import BackgroundTasks, WebSocket
+from fastapi.responses import FileResponse
+
+from docling_serve.datamodel.callback import ProgressCallbackRequest
+from docling_serve.datamodel.engines import TaskStatus
+from docling_serve.datamodel.responses import (
+    ConvertDocumentResponse,
+    MessageKind,
+    TaskStatusResponse,
+    WebsocketMessage,
+)
+from docling_serve.datamodel.task import Task
+from docling_serve.engines.base_orchestrator import (
+    BaseOrchestrator,
+    OrchestratorError,
+    TaskNotFoundError,
+)
+from docling_serve.settings import docling_serve_settings
+
+
+class ProgressInvalid(OrchestratorError):
+    pass
+
+
+class BaseAsyncOrchestrator(BaseOrchestrator):
+    def __init__(self):
+        self.tasks: dict[str, Task] = {}
+        self.task_subscribers: dict[str, set[WebSocket]] = {}
+
+    async def init_task_tracking(self, task: Task):
+        task_id = task.task_id
+        self.tasks[task.task_id] = task
+        self.task_subscribers[task_id] = set()
+
+    async def get_raw_task(self, task_id: str) -> Task:
+        if task_id not in self.tasks:
+            raise TaskNotFoundError()
+        return self.tasks[task_id]
+
+    async def task_status(self, task_id: str, wait: float = 0.0) -> Task:
+        return await self.get_raw_task(task_id=task_id)
+
+    async def task_result(
+        self, task_id: str, background_tasks: BackgroundTasks
+    ) -> Union[ConvertDocumentResponse, FileResponse, None]:
+        task = await self.get_raw_task(task_id=task_id)
+        if task.is_completed() and task.scratch_dir is not None:
+            if docling_serve_settings.single_use_results:
+                background_tasks.add_task(
+                    shutil.rmtree, task.scratch_dir, ignore_errors=True
+                )
+        return task.result
+
+    async def notify_task_subscribers(self, task_id: str):
+        if task_id not in self.task_subscribers:
+            raise RuntimeError(f"Task {task_id} does not have a subscribers list.")
+
+        task = await self.get_raw_task(task_id=task_id)
+        task_queue_position = await self.get_queue_position(task_id)
+        msg = TaskStatusResponse(
+            task_id=task.task_id,
+            task_status=task.task_status,
+            task_position=task_queue_position,
+            task_meta=task.processing_meta,
+        )
+        for websocket in self.task_subscribers[task_id]:
+            await websocket.send_text(
+                WebsocketMessage(message=MessageKind.UPDATE, task=msg).model_dump_json()
+            )
+            if task.is_completed():
+                await websocket.close()
+
+    async def notify_queue_positions(self):
+        for task_id in self.task_subscribers.keys():
+            # notify only pending tasks
+            if self.tasks[task_id].task_status != TaskStatus.PENDING:
+                continue
+
+            await self.notify_task_subscribers(task_id)
+
+    async def receive_task_progress(self, request: ProgressCallbackRequest):
+        raise NotImplementedError()

docling_serve/engines/async_orchestrator_factory.py

@@ -0,0 +1,21 @@
+from functools import lru_cache
+
+from docling_serve.datamodel.engines import AsyncEngine
+from docling_serve.engines.async_orchestrator import BaseAsyncOrchestrator
+from docling_serve.settings import docling_serve_settings
+
+
+@lru_cache
+def get_async_orchestrator() -> BaseAsyncOrchestrator:
+    if docling_serve_settings.eng_kind == AsyncEngine.LOCAL:
+        from docling_serve.engines.async_local.orchestrator import (
+            AsyncLocalOrchestrator,
+        )
+
+        return AsyncLocalOrchestrator()
+    elif docling_serve_settings.eng_kind == AsyncEngine.KFP:
+        from docling_serve.engines.async_kfp.orchestrator import AsyncKfpOrchestrator
+
+        return AsyncKfpOrchestrator()
+
+    raise RuntimeError(f"Engine {docling_serve_settings.eng_kind} not recognized.")

docling_serve/engines/base_orchestrator.py

@@ -1,11 +1,27 @@
 from abc import ABC, abstractmethod
+from typing import Optional, Union
 
-from docling_serve.datamodel.engines import Task
+from fastapi import BackgroundTasks
+from fastapi.responses import FileResponse
+
+from docling_serve.datamodel.convert import ConvertDocumentsOptions
+from docling_serve.datamodel.responses import ConvertDocumentResponse
+from docling_serve.datamodel.task import Task, TaskSource
+
+
+class OrchestratorError(Exception):
+    pass
+
+
+class TaskNotFoundError(OrchestratorError):
+    pass
 
 
 class BaseOrchestrator(ABC):
     @abstractmethod
-    async def enqueue(self, task) -> Task:
+    async def enqueue(
+        self, sources: list[TaskSource], options: ConvertDocumentsOptions
+    ) -> Task:
         pass
 
     @abstractmethod
@@ -13,9 +29,23 @@ class BaseOrchestrator(ABC):
         pass
 
     @abstractmethod
-    async def task_status(self, task_id: str) -> Task:
+    async def get_queue_position(self, task_id: str) -> Optional[int]:
         pass
 
     @abstractmethod
-    async def task_result(self, task_id: str):
+    async def task_status(self, task_id: str, wait: float = 0.0) -> Task:
+        pass
+
+    @abstractmethod
+    async def task_result(
+        self, task_id: str, background_tasks: BackgroundTasks
+    ) -> Union[ConvertDocumentResponse, FileResponse, None]:
+        pass
+
+    @abstractmethod
+    async def process_queue(self):
+        pass
+
+    @abstractmethod
+    async def warm_up_caches(self):
         pass

docling_serve/gradio_ui.py

@@ -1,22 +1,48 @@
+import base64
 import importlib
 import json
 import logging
-import os
+import ssl
 import tempfile
+import time
 from pathlib import Path
+from typing import Optional
 
+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
 
 logger = logging.getLogger(__name__)
 
+############################
+# Path of static artifacts #
+############################
+
+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@0.0.6"
+if (
+    docling_serve_settings.static_path is not None
+    and docling_serve_settings.static_path.is_dir()
+):
+    logo_path = str(docling_serve_settings.static_path / "logo.svg")
+    js_components_url = "/static/docling-components.js"
+
+
 ##############################
 # Head JS for web components #
 ##############################
-head = """
-    <script src="https://unpkg.com/@docling/docling-components@0.0.3" type="module"></script>
+head = f"""
+    <script src="{js_components_url}" type="module"></script>
 """
 
 #################
@@ -95,8 +121,29 @@ 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:{int(os.getenv('PORT', '5001'))}/health")
+    response = httpx.get(f"{get_api_endpoint()}/health")
     if response.status_code == 200:
         return "Healthy"
     return "Unhealthy"
@@ -112,6 +159,11 @@ 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)
@@ -123,6 +175,7 @@ def set_download_button_label(label_text: gr.State):
 
 
 def clear_outputs():
+    task_id_rendered = ""
     markdown_content = ""
     json_content = ""
     json_rendered_content = ""
@@ -131,6 +184,7 @@ def clear_outputs():
     doctags_content = ""
 
     return (
+        task_id_rendered,
         markdown_content,
         markdown_content,
         json_content,
@@ -150,12 +204,16 @@ def clear_file_input():
     return None
 
 
-def auto_set_return_as_file(url_input, file_input, image_export_mode):
+def auto_set_return_as_file(
+    url_input_value: str,
+    file_input_value: Optional[list[str]],
+    image_export_mode_value: str,
+):
     # If more than one input source is provided, return as file
     if (
-        (len(url_input.split(",")) > 1)
-        or (file_input and len(file_input) > 1)
-        or (image_export_mode == "referenced")
+        (len(url_input_value.split(",")) > 1)
+        or (file_input_value and len(file_input_value) > 1)
+        or (image_export_mode_value == "referenced")
     ):
         return True
     else:
@@ -173,10 +231,56 @@ 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,
@@ -185,12 +289,17 @@ def process_url(
     table_mode,
     abort_on_error,
     return_as_file,
+    do_code_enrichment,
+    do_formula_enrichment,
+    do_picture_classification,
+    do_picture_description,
 ):
     parameters = {
         "http_sources": [{"url": source} for source in input_sources.split(",")],
         "options": {
             "to_formats": to_formats,
             "image_export_mode": image_export_mode,
+            "pipeline": pipeline,
             "ocr": ocr,
             "force_ocr": force_ocr,
             "ocr_engine": ocr_engine,
@@ -199,6 +308,10 @@ def process_url(
             "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,
         },
     }
     if (
@@ -209,9 +322,12 @@ 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:{int(os.getenv('PORT', '5001'))}/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}")
@@ -221,14 +337,22 @@ 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,
     to_formats,
     image_export_mode,
+    pipeline,
     ocr,
     force_ocr,
     ocr_engine,
@@ -237,30 +361,46 @@ def process_file(
     table_mode,
     abort_on_error,
     return_as_file,
+    do_code_enrichment,
+    do_formula_enrichment,
+    do_picture_classification,
+    do_picture_description,
 ):
-    if not files or len(files) == 0 or files[0] == "":
+    if not files or len(files) == 0:
         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} for file in files
+    ]
 
     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(),
+        "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:{int(os.getenv('PORT', '5001'))}/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}")
@@ -270,8 +410,9 @@ 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):
@@ -342,17 +483,21 @@ with gr.Blocks(
     with gr.Row(elem_id="check_health"):
         # Logo
         with gr.Column(scale=1, min_width=90):
-            gr.Image(
-                "https://ds4sd.github.io/docling/assets/logo.png",
-                height=80,
-                width=80,
-                show_download_button=False,
-                show_label=False,
-                show_fullscreen_button=False,
-                container=False,
-                elem_id="logo",
-                scale=0,
-            )
+            try:
+                gr.Image(
+                    logo_path,
+                    height=80,
+                    width=80,
+                    show_download_button=False,
+                    show_label=False,
+                    show_fullscreen_button=False,
+                    container=False,
+                    elem_id="logo",
+                    scale=0,
+                )
+            except Exception:
+                logger.warning("Logo not found.")
+
         # Title
         with gr.Column(scale=1, min_width=200):
             gr.Markdown(
@@ -381,30 +526,31 @@ 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",
@@ -417,7 +563,7 @@ with gr.Blocks(
                     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
@@ -426,14 +572,14 @@ 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(
@@ -445,6 +591,13 @@ 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)
@@ -465,32 +618,53 @@ 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)
+        with gr.Row():
+            with gr.Column():
+                do_code_enrichment = gr.Checkbox(
+                    label="Enable code enrichment", value=False
+                )
+                do_formula_enrichment = gr.Checkbox(
+                    label="Enable formula enrichment", value=False
+                )
+            with gr.Column():
+                do_picture_classification = gr.Checkbox(
+                    label="Enable picture classification", value=False
+                )
+                do_picture_description = gr.Checkbox(
+                    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"):
@@ -530,14 +704,11 @@ with gr.Blocks(
         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,
@@ -547,12 +718,17 @@ 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,
@@ -561,7 +737,21 @@ with gr.Blocks(
             table_mode,
             abort_on_error,
             return_as_file,
+            do_code_enrichment,
+            do_formula_enrichment,
+            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,
@@ -592,21 +782,20 @@ 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,
@@ -616,12 +805,17 @@ 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,
@@ -630,7 +824,21 @@ with gr.Blocks(
             table_mode,
             abort_on_error,
             return_as_file,
+            do_code_enrichment,
+            do_formula_enrichment,
+            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,
@@ -661,4 +869,6 @@ 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]
+    )

docling_serve/response_preparation.py

@@ -1,13 +1,12 @@
 import logging
 import os
 import shutil
-import tempfile
 import time
 from collections.abc import Iterable
 from pathlib import Path
 from typing import Union
 
-from fastapi import BackgroundTasks, HTTPException
+from fastapi import HTTPException
 from fastapi.responses import FileResponse
 
 from docling.datamodel.base_models import OutputFormat
@@ -46,7 +45,7 @@ def _export_document_as_content(
         if export_md:
             document.md_content = new_doc.export_to_markdown(image_mode=image_mode)
         if export_doctags:
-            document.doctags_content = new_doc.export_to_document_tokens()
+            document.doctags_content = new_doc.export_to_doctags()
     elif conv_res.status == ConversionStatus.SKIPPED:
         raise HTTPException(status_code=400, detail=conv_res.errors)
     else:
@@ -124,9 +123,9 @@ def _export_documents_as_files(
 
 
 def process_results(
-    background_tasks: BackgroundTasks,
     conversion_options: ConvertDocumentsOptions,
     conv_results: Iterable[ConversionResult],
+    work_dir: Path,
 ) -> Union[ConvertDocumentResponse, FileResponse]:
     # Let's start by processing the documents
     try:
@@ -183,7 +182,6 @@ def process_results(
     # Multiple documents were processed, or we are forced returning as a file
     else:
         # Temporary directory to store the outputs
-        work_dir = Path(tempfile.mkdtemp(prefix="docling_"))
         output_dir = work_dir / "output"
         output_dir.mkdir(parents=True, exist_ok=True)
 
@@ -203,7 +201,6 @@ def process_results(
         )
 
         files = os.listdir(output_dir)
-
         if len(files) == 0:
             raise HTTPException(status_code=500, detail="No documents were exported.")
 
@@ -216,7 +213,7 @@ def process_results(
 
         # Other cleanups after the response is sent
         # Output directory
-        background_tasks.add_task(shutil.rmtree, work_dir, ignore_errors=True)
+        # background_tasks.add_task(shutil.rmtree, work_dir, ignore_errors=True)
 
         response = FileResponse(
             file_path, filename=file_path.name, media_type="application/zip"

docling_serve/settings.py

@@ -1,7 +1,10 @@
+import sys
 from pathlib import Path
 from typing import Optional, Union
 
+from pydantic import AnyUrl, model_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
+from typing_extensions import Self
 
 from docling_serve.datamodel.engines import AsyncEngine
 
@@ -16,6 +19,10 @@ class UvicornSettings(BaseSettings):
     reload: bool = False
     root_path: str = ""
     proxy_headers: bool = True
+    timeout_keep_alive: int = 60
+    ssl_certfile: Optional[Path] = None
+    ssl_keyfile: Optional[Path] = None
+    ssl_keyfile_password: Optional[str] = None
     workers: Union[int, None] = None
 
 
@@ -28,10 +35,50 @@ class DoclingServeSettings(BaseSettings):
     )
 
     enable_ui: bool = False
+    api_host: str = "localhost"
     artifacts_path: Optional[Path] = None
+    static_path: Optional[Path] = None
+    scratch_path: Optional[Path] = None
+    single_use_results: bool = True
+    options_cache_size: int = 2
+    enable_remote_services: bool = False
+    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] = ["*"]
 
     eng_kind: AsyncEngine = AsyncEngine.LOCAL
+    # Local engine
     eng_loc_num_workers: int = 2
+    # KFP engine
+    eng_kfp_endpoint: Optional[AnyUrl] = None
+    eng_kfp_token: Optional[str] = None
+    eng_kfp_ca_cert_path: Optional[str] = None
+    eng_kfp_self_callback_endpoint: Optional[str] = None
+    eng_kfp_self_callback_token_path: Optional[Path] = None
+    eng_kfp_self_callback_ca_cert_path: Optional[Path] = None
+
+    eng_kfp_experimental: bool = False
+
+    @model_validator(mode="after")
+    def engine_settings(self) -> Self:
+        # Validate KFP engine settings
+        if self.eng_kind == AsyncEngine.KFP:
+            if self.eng_kfp_endpoint is None:
+                raise ValueError("KFP endpoint is required when using the KFP engine.")
+
+        if self.eng_kind == AsyncEngine.KFP:
+            if not self.eng_kfp_experimental:
+                raise ValueError(
+                    "KFP is not yet working. To enable the development version, you must set DOCLING_SERVE_ENG_KFP_EXPERIMENTAL=true."
+                )
+
+        return self
 
 
 uvicorn_settings = UvicornSettings()

docling_serve/storage.py

@@ -0,0 +1,16 @@
+import tempfile
+from functools import lru_cache
+from pathlib import Path
+
+from docling_serve.settings import docling_serve_settings
+
+
+@lru_cache
+def get_scratch() -> Path:
+    scratch_dir = (
+        docling_serve_settings.scratch_path
+        if docling_serve_settings.scratch_path is not None
+        else Path(tempfile.mkdtemp(prefix="docling_"))
+    )
+    scratch_dir.mkdir(exist_ok=True, parents=True)
+    return scratch_dir

docs/README.md

@@ -0,0 +1,8 @@
+# Dolcing Serve documentation
+
+This documentation pages explore the webserver configurations, runtime options, deployment examples as well as development best practices.
+
+- [Configuration](./configuration.md)
+- [Advance usage](./usage.md)
+- [Deployment](./deployment.md)
+- [Development](./development.md)

docs/configuration.md

@@ -0,0 +1,78 @@
+# Configuration
+
+The `docling-serve` executable allows to configure the server via command line
+options as well as environment variables.
+Configurations are divided between the settings used for the `uvicorn` asgi
+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
+> via the CLI command line options. Please use environment variables in this
+> type of deployments.
+
+## Webserver configuration
+
+The following table shows the options which are propagated directly to the
+`uvicorn` webserver runtime.
+
+| CLI option | ENV | Default | Description |
+| -----------|-----|---------|-------------|
+| `--host` | `UVICORN_HOST` | `0.0.0.0` for `run`, `localhost` for `dev` | THe host to serve on. |
+| `--port` | `UVICORN_PORT` | `5001` | The port to serve on. |
+| `--reload` | `UVICORN_RELOAD` | `false` for `run`, `true` for `dev` | Enable auto-reload of the server when (code) files change. |
+| `--workers` | `UVICORN_WORKERS` | `1` | Use multiple worker processes. |
+| `--root-path` | `UVICORN_ROOT_PATH` | `""` | The root path is used to tell your app that it is being served to the outside world with some |
+| `--proxy-headers` | `UVICORN_PROXY_HEADERS` | `true` | Enable/Disable X-Forwarded-Proto, X-Forwarded-For, X-Forwarded-Port to populate remote address info. |
+| `--timeout-keep-alive` | `UVICORN_TIMEOUT_KEEP_ALIVE` | `60` | Timeout for the server response. |
+| `--ssl-certfile` | `UVICORN_SSL_CERTFILE` |  | SSL certificate file. |
+| `--ssl-keyfile` | `UVICORN_SSL_KEYFILE` |  | SSL key file. |
+| `--ssl-keyfile-password` | `UVICORN_SSL_KEYFILE_PASSWORD` |  | SSL keyfile password. |
+
+## Docling Serve configuration
+
+THe following table describes the options to configure the Docling Serve app.
+
+| CLI option | ENV | Default | Description |
+| -----------|-----|---------|-------------|
+| `--artifacts-path` | `DOCLING_SERVE_ARTIFACTS_PATH` | unset | If set to a valid directory, the model weights will be loaded from this path |
+|  | `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_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_MAX_DOCUMENT_TIMEOUT` | `604800` (7 days) | The maximum time 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_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. |
+|  | `DOCLING_SERVE_CORS_HEADERS` | `["*"]` | A list of HTTP request headers that should be supported for cross-origin requests. |
+|  | `DOCLING_SERVE_ENG_KIND` | `local` | The compute engine to use for the async tasks. Possible values are `local` and `kfp`. See below for more configurations of the engines. |
+
+### Compute engine
+
+Docling Serve can be deployed with several possible of compute engine.
+The selected compute engine will be running all the async jobs.
+
+#### Local engine
+
+The following table describes the options to configure the Docling Serve KFP engine.
+
+| ENV | Default | Description |
+|-----|---------|-------------|
+| `DOCLING_SERVE_ENG_LOC_NUM_WORKERS` | 2 | Number of workers/threads processing the incoming tasks. |
+
+#### KFP engine
+
+The following table describes the options to configure the Docling Serve KFP engine.
+
+| ENV | Default | Description |
+|-----|---------|-------------|
+| `DOCLING_SERVE_ENG_KFP_ENDPOINT` |  | Must be set to the Kubeflow Pipeline endpoint. When using the in-cluster deployment, make sure to use the cluster endpoint, e.g. `https://NAME.NAMESPACE.svc.cluster.local:8888`  |
+| `DOCLING_SERVE_ENG_KFP_TOKEN` |  | The authentication token for KFP. For in-cluster deployment, the app will load automatically the token of the ServiceAccount. |
+| `DOCLING_SERVE_ENG_KFP_CA_CERT_PATH` |  | Path to the CA certificates for the KFP endpoint. For in-cluster deployment, the app will load automatically the internal CA. |
+| `DOCLING_SERVE_ENG_KFP_SELF_CALLBACK_ENDPOINT` |  | If set, it enables internal callbacks providing status update of the KFP job. Usually something like `https://NAME.NAMESPACE.svc.cluster.local:5001/v1alpha/callback/task/progress`. |
+| `DOCLING_SERVE_ENG_KFP_SELF_CALLBACK_TOKEN_PATH` |  | The token used for authenticating the progress callback. For cluster-internal workloads, use `/run/secrets/kubernetes.io/serviceaccount/token`. |
+| `DOCLING_SERVE_ENG_KFP_SELF_CALLBACK_CA_CERT_PATH` |  | The CA certificate for the progress callback. For cluster-inetrnal workloads, use `/var/run/secrets/kubernetes.io/serviceaccount/service-ca.crt`. |

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]

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

@@ -0,0 +1,192 @@
+# This example deployment configures Docling Serve with a OAuth-Proxy sidecar and TLS termination
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: docling-serve
+  labels:
+    app: docling-serve
+  annotations:
+    serviceaccounts.openshift.io/oauth-redirectreference.primary: '{"kind":"OAuthRedirectReference","apiVersion":"v1","reference":{"kind":"Route","name":"docling-serve"}}'
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: docling-serve-oauth
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:auth-delegator
+subjects:
+- kind: ServiceAccount
+  name: docling-serve
+  namespace: docling
+---
+apiVersion: route.openshift.io/v1
+kind: Route
+metadata:
+  name: docling-serve
+  labels:
+    app: docling-serve
+    component: docling-serve-api
+spec:
+  to:
+    kind: Service
+    name: docling-serve
+  port:
+    targetPort: oauth
+  tls:
+    termination: Reencrypt
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: docling-serve
+  labels:
+    app: docling-serve
+    component: docling-serve-api
+  annotations:
+    service.alpha.openshift.io/serving-cert-secret-name: docling-serve-tls
+spec:
+  ports:
+  - name: oauth
+    port: 8443
+    targetPort: oauth
+  - 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
+      serviceAccountName: docling-serve
+      containers:
+        - name: api
+          resources:
+            limits:
+              cpu: 2000m
+              memory: 2Gi
+            requests:
+              cpu: 800m
+              memory: 1Gi
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: http
+              scheme: HTTPS
+            initialDelaySeconds: 10
+            timeoutSeconds: 2
+            periodSeconds: 5
+            successThreshold: 1
+            failureThreshold: 3
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: http
+              scheme: HTTPS
+            initialDelaySeconds: 3
+            timeoutSeconds: 4
+            periodSeconds: 10
+            successThreshold: 1
+            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
+              value: '/etc/tls/private/tls.key'
+          ports:
+            - name: http
+              containerPort: 5001
+              protocol: TCP
+          volumeMounts:
+            - name: proxy-tls
+              mountPath: /etc/tls/private
+          imagePullPolicy: Always
+          image: 'ghcr.io/docling-project/docling-serve-cpu:fix-ui-with-https'
+        - name: oauth-proxy
+          resources:
+            limits:
+              cpu: 100m
+              memory: 256Mi
+            requests:
+              cpu: 100m
+              memory: 256Mi
+          readinessProbe:
+            httpGet:
+              path: /oauth/healthz
+              port: oauth
+              scheme: HTTPS
+            initialDelaySeconds: 5
+            timeoutSeconds: 1
+            periodSeconds: 5
+            successThreshold: 1
+            failureThreshold: 3
+          livenessProbe:
+            httpGet:
+              path: /oauth/healthz
+              port: oauth
+              scheme: HTTPS
+            initialDelaySeconds: 30
+            timeoutSeconds: 1
+            periodSeconds: 5
+            successThreshold: 1
+            failureThreshold: 3
+          ports:
+            - name: oauth
+              containerPort: 8443
+              protocol: TCP
+          imagePullPolicy: IfNotPresent
+          volumeMounts:
+            - name: proxy-tls
+              mountPath: /etc/tls/private
+          env:
+            - name: NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          image: 'registry.redhat.io/openshift4/ose-oauth-proxy:v4.13'
+          args:
+            - '--https-address=:8443'
+            - '--provider=openshift'
+            - '--openshift-service-account=docling-serve'
+            - '--upstream=https://docling-serve.$(NAMESPACE).svc.cluster.local:5001'
+            - '--upstream-ca=/var/run/secrets/kubernetes.io/serviceaccount/service-ca.crt'
+            - '--tls-cert=/etc/tls/private/tls.crt'
+            - '--tls-key=/etc/tls/private/tls.key'
+            - '--cookie-secret=SECRET'
+            - '--openshift-delegate-urls={"/": {"group":"route.openshift.io","resource":"routes","verb":"get","name":"docling-serve","namespace":"$(NAMESPACE)"}}'
+            - '--openshift-sar={"namespace":"$(NAMESPACE)","resource":"routes","resourceName":"docling-serve","verb":"get","resourceAPIGroup":"route.openshift.io"}'
+            - '--skip-auth-regex=''(^/health|^/docs)'''
+      volumes:
+        - name: proxy-tls
+          secret:
+            secretName: docling-serve-tls
+            defaultMode: 420

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'

docs/deployment.md

@@ -0,0 +1,194 @@
+# 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)
+
+This deployment has the following features:
+
+- TLS encryption between all components (using the cluster-internal CA authority).
+- Authentication via a secure `oauth-proxy` sidecar.
+- Expose the service using a secure OpenShift `Route`
+
+Install the app with:
+
+```sh
+oc apply -f docs/deploy-examples/docling-serve-oauth.yaml
+```
+
+For using the API:
+
+```sh
+# Retrieve the endpoint
+DOCLING_NAME=docling-serve
+DOCLING_ROUTE="https://$(oc get routes ${DOCLING_NAME} --template={{.spec.host}})"
+
+# Retrieve the authentication token
+OCP_AUTH_TOKEN=$(oc whoami --show-token)
+
+# Make a test query
+curl -X 'POST' \
+  "${DOCLING_ROUTE}/v1alpha/convert/source/async" \
+  -H "Authorization: Bearer ${OCP_AUTH_TOKEN}" \
+  -H "accept: application/json" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}]
+  }'
+```

docs/development.md

@@ -0,0 +1,57 @@
+# Development
+
+## Install dependencies
+
+### CPU only
+
+```sh
+# Install uv if not already available
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Install dependencies
+uv sync --extra cpu
+```
+
+### Cuda GPU
+
+For GPU support use the following command:
+
+```sh
+# Install dependencies
+uv sync
+```
+
+### Gradio UI and different OCR backends
+
+`/ui` endpoint using `gradio` and different OCR backends can be enabled via package extras:
+
+```sh
+# Enable ui and rapidocr
+uv sync --extra ui --extra rapidocr
+```
+
+```sh
+# Enable tesserocr
+uv sync --extra tesserocr
+```
+
+See `[project.optional-dependencies]` section in `pyproject.toml` for full list of options and runtime options with `uv run docling-serve --help`.
+
+### Run the server
+
+The `docling-serve` executable is a convenient script for launching the webserver both in
+development and production mode.
+
+```sh
+# Run the server in development mode
+# - reload is enabled by default
+# - listening on the 127.0.0.1 address
+# - ui is enabled by default
+docling-serve dev
+
+# Run the server in production mode
+# - reload is disabled by default
+# - listening on the 0.0.0.0 address
+# - ui is disabled by default
+docling-serve run
+```

docs/usage.md

@@ -0,0 +1,350 @@
+# Usage
+
+The API provides two endpoints: one for urls, one for files. This is necessary to send files directly in binary format instead of base64-encoded strings.
+
+## Common parameters
+
+On top of the source of file (see below), both endpoints support the same parameters, which are almost the same as the Docling CLI.
+
+- `from_formats` (List[str]): Input format(s) to convert from. Allowed values: `docx`, `pptx`, `html`, `image`, `pdf`, `asciidoc`, `md`. Defaults to all formats.
+- `to_formats` (List[str]): Output format(s) to convert to. Allowed values: `md`, `json`, `html`, `text`, `doctags`. Defaults to `md`.
+- `pipeline` (str). The choice of which pipeline to use. Allowed values are `standard` and `vlm`. Defaults to `standard`.
+- `do_ocr` (bool): If enabled, the bitmap content will be processed using OCR. Defaults to `True`.
+- `image_export_mode`: Image export mode for the document (only in case of JSON, Markdown or HTML). Allowed values: embedded, placeholder, referenced. Optional, defaults to `embedded`.
+- `force_ocr` (bool): If enabled, replace any existing text with OCR-generated text over the full content. Defaults to `False`.
+- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesseract_cli`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`.
+- `ocr_lang` (List[str]): List of languages used by the OCR engine. Note that each OCR engine has different values for the language names. Defaults to empty.
+- `pdf_backend` (str): PDF backend to use. Allowed values: `pypdfium2`, `dlparse_v1`, `dlparse_v2`, `dlparse_v4`. Defaults to `dlparse_v4`.
+- `table_mode` (str): Table mode to use. Allowed values: `fast`, `accurate`. Defaults to `fast`.
+- `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.
+- `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.
+- `do_picture_classification` (bool): If enabled, classify pictures in documents. Defaults to false.
+- `do_picture_description` (bool): If enabled, describe pictures in documents. Defaults to false.
+- `picture_description_local` (dict): Options for running a local vision-language model in the picture description. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with picture_description_api.
+- `picture_description_api` (dict): API details for using a vision-language model in the picture description. This parameter is mutually exclusive with picture_description_local.
+- `include_images` (bool): If enabled, images will be extracted from the document. Defaults to false.
+- `images_scale` (float): Scale factor for images. Defaults to 2.0.
+
+## Convert endpoints
+
+### Source endpoint
+
+The endpoint is `/v1alpha/convert/source`, listening for POST requests of JSON payloads.
+
+On top of the above parameters, you must send the URL(s) of the document you want process with either the `http_sources` or `file_sources` fields.
+The first is fetching URL(s) (optionally using with extra headers), the second allows to provide documents as base64-encoded strings.
+No `options` is required, they can be partially or completely omitted.
+
+Simple payload example:
+
+```json
+{
+  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
+}
+```
+
+<details>
+
+<summary>Complete payload example:</summary>
+
+```json
+{
+  "options": {
+    "from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
+    "to_formats": ["md", "json", "html", "text", "doctags"],
+    "image_export_mode": "placeholder",
+    "do_ocr": true,
+    "force_ocr": false,
+    "ocr_engine": "easyocr",
+    "ocr_lang": ["en"],
+    "pdf_backend": "dlparse_v2",
+    "table_mode": "fast",
+    "abort_on_error": false,
+    "return_as_file": false,
+  },
+  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
+}
+```
+
+</details>
+
+<details>
+
+<summary>CURL example:</summary>
+
+```sh
+curl -X 'POST' \
+  'http://localhost:5001/v1alpha/convert/source' \
+  -H 'accept: application/json' \
+  -H 'Content-Type: application/json' \
+  -d '{
+  "options": {
+    "from_formats": [
+      "docx",
+      "pptx",
+      "html",
+      "image",
+      "pdf",
+      "asciidoc",
+      "md",
+      "xlsx"
+    ],
+    "to_formats": ["md", "json", "html", "text", "doctags"],
+    "image_export_mode": "placeholder",
+    "do_ocr": true,
+    "force_ocr": false,
+    "ocr_engine": "easyocr",
+    "ocr_lang": [
+      "fr",
+      "de",
+      "es",
+      "en"
+    ],
+    "pdf_backend": "dlparse_v2",
+    "table_mode": "fast",
+    "abort_on_error": false,
+    "return_as_file": false,
+    "do_table_structure": true,
+    "include_images": true,
+    "images_scale": 2
+  },
+  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
+}'
+```
+
+</details>
+
+<details>
+<summary>Python example:</summary>
+
+```python
+import httpx
+
+async_client = httpx.AsyncClient(timeout=60.0)
+url = "http://localhost:5001/v1alpha/convert/source"
+payload = {
+  "options": {
+    "from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
+    "to_formats": ["md", "json", "html", "text", "doctags"],
+    "image_export_mode": "placeholder",
+    "do_ocr": True,
+    "force_ocr": False,
+    "ocr_engine": "easyocr",
+    "ocr_lang": "en",
+    "pdf_backend": "dlparse_v2",
+    "table_mode": "fast",
+    "abort_on_error": False,
+    "return_as_file": False,
+  },
+  "http_sources": [{"url": "https://arxiv.org/pdf/2206.01062"}]
+}
+
+response = await async_client_client.post(url, json=payload)
+
+data = response.json()
+```
+
+</details>
+
+#### File as base64
+
+The `file_sources` argument in the endpoint allows to send files as base64-encoded strings.
+When your PDF or other file type is too large, encoding it and passing it inline to curl
+can lead to an “Argument list too long” error on some systems. To avoid this, we write
+the JSON request body to a file and have curl read from that file.
+
+<details>
+<summary>CURL steps:</summary>
+
+```sh
+# 1. Base64-encode the file
+B64_DATA=$(base64 -w 0 /path/to/file/pdf-to-convert.pdf)
+
+# 2. Build the JSON with your options
+cat <<EOF > /tmp/request_body.json
+{
+  "options": {
+  },
+  "file_sources": [{
+    "base64_string": "${B64_DATA}",
+    "filename": "pdf-to-convert.pdf"
+  }]
+}
+EOF
+
+# 3. POST the request to the docling service
+curl -X POST "localhost:5001/v1alpha/convert/source" \
+     -H "Content-Type: application/json" \
+     -d @/tmp/request_body.json
+```
+
+</details>
+
+### File endpoint
+
+The endpoint is: `/v1alpha/convert/file`, listening for POST requests of Form payloads (necessary as the files are sent as multipart/form data). You can send one or multiple files.
+
+<details>
+<summary>CURL example:</summary>
+
+```sh
+curl -X 'POST' \
+  'http://127.0.0.1:5001/v1alpha/convert/file' \
+  -H 'accept: application/json' \
+  -H 'Content-Type: multipart/form-data' \
+  -F 'ocr_engine=easyocr' \
+  -F 'pdf_backend=dlparse_v2' \
+  -F 'from_formats=pdf' \
+  -F 'from_formats=docx' \
+  -F 'force_ocr=false' \
+  -F 'image_export_mode=embedded' \
+  -F 'ocr_lang=en' \
+  -F 'ocr_lang=pl' \
+  -F 'table_mode=fast' \
+  -F 'files=@2206.01062v1.pdf;type=application/pdf' \
+  -F 'abort_on_error=false' \
+  -F 'to_formats=md' \
+  -F 'to_formats=text' \
+  -F 'return_as_file=false' \
+  -F 'do_ocr=true'
+```
+
+</details>
+
+<details>
+<summary>Python example:</summary>
+
+```python
+import httpx
+
+async_client = httpx.AsyncClient(timeout=60.0)
+url = "http://localhost:5001/v1alpha/convert/file"
+parameters = {
+"from_formats": ["docx", "pptx", "html", "image", "pdf", "asciidoc", "md", "xlsx"],
+"to_formats": ["md", "json", "html", "text", "doctags"],
+"image_export_mode": "placeholder",
+"do_ocr": True,
+"force_ocr": False,
+"ocr_engine": "easyocr",
+"ocr_lang": ["en"],
+"pdf_backend": "dlparse_v2",
+"table_mode": "fast",
+"abort_on_error": False,
+"return_as_file": False
+}
+
+current_dir = os.path.dirname(__file__)
+file_path = os.path.join(current_dir, '2206.01062v1.pdf')
+
+files = {
+    'files': ('2206.01062v1.pdf', open(file_path, 'rb'), 'application/pdf'),
+}
+
+response = await async_client.post(url, files=files, data={"parameters": json.dumps(parameters)})
+assert response.status_code == 200, "Response should be 200 OK"
+
+data = response.json()
+```
+
+</details>
+
+### Picture description options
+
+When the picture description enrichment is activated, users may specify which model and which execution mode to use for this task. There are two choices for the execution mode: _local_ will run the vision-language model directly, _api_ will invoke an external API endpoint.
+
+The local option is specified with:
+
+```jsonc
+{
+  "picture_description_local": {
+    "repo_id": "",  // Repository id from the Hugging Face Hub.
+    "generation_config": {"max_new_tokens": 200, "do_sample": false},  // HF generation config.
+    "prompt": "Describe this image in a few sentences. ",  // Prompt used when calling the vision-language model.
+  }
+}
+```
+
+The possible values for `generation_config` are documented in the [Hugging Face text generation docs](https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.GenerationConfig).
+
+The api option is specified with:
+
+```jsonc
+{
+  "picture_description_api": {
+    "url": "",  // Endpoint which accepts openai-api compatible requests.
+    "headers": {},  // Headers used for calling the API endpoint. For example, it could include authentication headers.
+    "params": {},  // Model parameters.
+    "timeout": 20,  // Timeout for the API request.
+    "prompt": "Describe this image in a few sentences. ",  // Prompt used when calling the vision-language model.
+  }
+}
+```
+
+Example URLs are:
+
+- `http://localhost:8000/v1/chat/completions` for the local vllm api, with example `params`:
+  - the `HuggingFaceTB/SmolVLM-256M-Instruct` model
+
+    ```json
+    {
+        "model": "HuggingFaceTB/SmolVLM-256M-Instruct",
+        "max_completion_tokens": 200,
+    }
+    ```
+  
+  - the `ibm-granite/granite-vision-3.2-2b` model
+
+    ```json
+    {
+        "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`:
+  - the `granite3.2-vision:2b` model
+
+    ```json
+    {
+        "model": "granite3.2-vision:2b"
+    }
+    ```  
+
+Note that when using `picture_description_api`, the server must be launched with `DOCLING_SERVE_ENABLE_REMOTE_SERVICES=true`.
+
+## Response format
+
+The response can be a JSON Document or a File.
+
+- If you process only one file, the response will be a JSON document with the following format:
+
+  ```jsonc
+  {
+    "document": {
+      "md_content": "",
+      "json_content": {},
+      "html_content": "",
+      "text_content": "",
+      "doctags_content": ""
+      },
+    "status": "<success|partial_success|skipped|failure>",
+    "processing_time": 0.0,
+    "timings": {},
+    "errors": []
+  }
+  ```
+
+  Depending on the value you set in `output_formats`, the different items will be populated with their respective results or empty.
+
+  `processing_time` is the Docling processing time in seconds, and `timings` (when enabled in the backend) provides the detailed
+  timing of all the internal Docling components.
+
+- If you set the parameter `return_as_file` to True, the response will be a zip file.
+- If multiple files are generated (multiple inputs, or one input but multiple outputs with `return_as_file` True), the response will be a zip file.
+
+## Asynchronous API
+
+TBA

os-packages.txt

@@ -4,5 +4,3 @@ tesseract-langpack-eng
 leptonica-devel
 libglvnd-glx
 glib2
-wget
-git

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.5.0"  # DO NOT EDIT, updated automatically
+version = "0.10.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [
@@ -30,9 +30,11 @@ classifiers = [
 ]
 requires-python = ">=3.10"
 dependencies = [
-    "docling~=2.25.1",
+    "docling[vlm]~=2.28",
+    "mlx-vlm~=0.1.12; sys_platform == 'darwin' and platform_machine == 'arm64'",
     "fastapi[standard]~=0.115",
     "httpx~=0.28",
+    "kfp[kubernetes]>=2.10.0",
     "pydantic~=2.10",
     "pydantic-settings~=2.4",
     "python-multipart>=0.0.14,<0.1.0",
@@ -43,7 +45,8 @@ 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"
@@ -63,8 +66,9 @@ cu124 = [
 
 [dependency-groups]
 dev = [
+    "asgi-lifespan~=2.0",
     "mypy~=1.11",
-    "pre-commit~=3.8",
+    "pre-commit-uv~=4.1",
     "pytest~=8.3",
     "pytest-asyncio~=0.24",
     "pytest-check~=2.4",
@@ -80,6 +84,10 @@ conflicts = [
     { extra = "cu124" },
   ],
 ]
+environments = ["sys_platform != 'darwin' or platform_machine != 'x86_64'"]
+override-dependencies = [
+  "urllib3~=2.0"
+]
 
 [tool.uv.sources]
 torch = [
@@ -102,17 +110,18 @@ url = "https://download.pytorch.org/whl/cu124"
 explicit = true
 
 [tool.setuptools.packages.find]
-include = ["docling_serve"]
+include = ["docling_serve*"]
+namespaces = true
 
 [project.scripts]
 docling-serve = "docling_serve.__main__:main"
 
 [project.urls]
-Homepage = "https://github.com/DS4SD/docling-serve"
+Homepage = "https://github.com/docling-project/docling-serve"
 # Documentation = "https://ds4sd.github.io/docling"
-Repository = "https://github.com/DS4SD/docling-serve"
-Issues = "https://github.com/DS4SD/docling-serve/issues"
-Changelog = "https://github.com/DS4SD/docling-serve/blob/main/CHANGELOG.md"
+Repository = "https://github.com/docling-project/docling-serve"
+Issues = "https://github.com/docling-project/docling-serve/issues"
+Changelog = "https://github.com/docling-project/docling-serve/blob/main/CHANGELOG.md"
 
 [tool.ruff]
 target-version = "py310"
@@ -194,6 +203,9 @@ module = [
     "tesserocr.*",
     "rapidocr_onnxruntime.*",
     "requests.*",
+    "kfp.*",
+    "kfp_server_api.*",
+    "mlx_vlm.*",
 ]
 ignore_missing_imports = true
 

tests/test_1-file-all-outputs.py

@@ -47,9 +47,7 @@ async def test_convert_file(async_client):
         "files": ("2206.01062v1.pdf", open(file_path, "rb"), "application/pdf"),
     }
 
-    response = await async_client.post(
-        url, files=files, data={"options": json.dumps(options)}
-    )
+    response = await async_client.post(url, files=files, data=options)
     assert response.status_code == 200, "Response should be 200 OK"
 
     data = response.json()
@@ -92,16 +90,11 @@ 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 +116,7 @@ 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'])}",
         )

tests/test_1-file-async.py

@@ -0,0 +1,69 @@
+import json
+import time
+from pathlib import Path
+
+import httpx
+import pytest
+import pytest_asyncio
+
+
+@pytest_asyncio.fixture
+async def async_client():
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        yield client
+
+
+@pytest.mark.asyncio
+async def test_convert_url(async_client):
+    """Test convert URL to all outputs"""
+
+    base_url = "http://localhost:5001/v1alpha"
+    payload = {
+        "to_formats": ["md", "json", "html"],
+        "image_export_mode": "placeholder",
+        "ocr": False,
+        "abort_on_error": False,
+        "return_as_file": False,
+    }
+
+    file_path = Path(__file__).parent / "2206.01062v1.pdf"
+    files = {
+        "files": (file_path.name, file_path.open("rb"), "application/pdf"),
+    }
+
+    for n in range(1):
+        response = await async_client.post(
+            f"{base_url}/convert/file/async", files=files, data=payload
+        )
+        assert response.status_code == 200, "Response should be 200 OK"
+
+    task = response.json()
+
+    print(json.dumps(task, indent=2))
+
+    while task["task_status"] not in ("success", "failure"):
+        response = await async_client.get(f"{base_url}/status/poll/{task['task_id']}")
+        assert response.status_code == 200, "Response should be 200 OK"
+        task = response.json()
+        print(f"{task['task_status']=}")
+        print(f"{task['task_position']=}")
+
+        time.sleep(2)
+
+    assert task["task_status"] == "success"
+
+    result_resp = await async_client.get(f"{base_url}/result/{task['task_id']}")
+    assert result_resp.status_code == 200, "Response should be 200 OK"
+    result = result_resp.json()
+
+    assert "md_content" in result["document"]
+    assert result["document"]["md_content"] is not None
+    assert len(result["document"]["md_content"]) > 10
+
+    assert "html_content" in result["document"]
+    assert result["document"]["html_content"] is not None
+    assert len(result["document"]["html_content"]) > 10
+
+    assert "json_content" in result["document"]
+    assert result["document"]["json_content"] is not None
+    assert result["document"]["json_content"]["schema_name"] == "DoclingDocument"

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'])}",
         )

tests/test_1-url-async-ws.py

@@ -28,6 +28,16 @@ async def test_convert_url(async_client: httpx.AsyncClient):
             "ocr": True,
             "abort_on_error": False,
             "return_as_file": False,
+            # "do_picture_description": True,
+            # "picture_description_api": {
+            #     "url": "http://localhost:11434/v1/chat/completions",
+            #     "params": {
+            #         "model": "granite3.2-vision:2b",
+            #     }
+            # },
+            # "picture_description_local": {
+            #     "repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct",
+            # },
         },
         # "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}],
         "file_sources": [{"base64_string": encoded_doc, "filename": doc_filename.name}],

tests/test_1-url-async.py

@@ -38,7 +38,7 @@ async def test_convert_url(async_client):
     }
     print(json.dumps(payload, indent=2))
 
-    for n in range(5):
+    for n in range(3):
         response = await async_client.post(
             f"{base_url}/convert/source/async", json=payload
         )

tests/test_2-files-all-outputs.py

@@ -1,4 +1,3 @@
-import json
 import os
 
 import httpx
@@ -48,9 +47,7 @@ async def test_convert_file(async_client):
         ("files", ("2408.09869v5.pdf", open(file_path, "rb"), "application/pdf")),
     ]
 
-    response = await async_client.post(
-        url, files=files, data={"options": json.dumps(options)}
-    )
+    response = await async_client.post(url, files=files, data=options)
     assert response.status_code == 200, "Response should be 200 OK"
 
     # Check for zip file attachment

tests/test_2-urls-async-all-outputs.py

@@ -0,0 +1,88 @@
+import json
+import time
+
+import httpx
+import pytest
+import pytest_asyncio
+from pytest_check import check
+
+
+@pytest_asyncio.fixture
+async def async_client():
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        yield client
+
+
+@pytest.mark.asyncio
+async def test_convert_url(async_client):
+    """Test convert URL to all outputs"""
+    base_url = "http://localhost:5001/v1alpha"
+    payload = {
+        "options": {
+            "from_formats": [
+                "docx",
+                "pptx",
+                "html",
+                "image",
+                "pdf",
+                "asciidoc",
+                "md",
+                "xlsx",
+            ],
+            "to_formats": ["md", "json", "html", "text", "doctags"],
+            "image_export_mode": "placeholder",
+            "ocr": True,
+            "force_ocr": False,
+            "ocr_engine": "easyocr",
+            "ocr_lang": ["en"],
+            "pdf_backend": "dlparse_v2",
+            "table_mode": "fast",
+            "abort_on_error": False,
+            "return_as_file": False,
+        },
+        "http_sources": [
+            {"url": "https://arxiv.org/pdf/2206.01062"},
+            {"url": "https://arxiv.org/pdf/2408.09869"},
+        ],
+    }
+
+    response = await async_client.post(f"{base_url}/convert/source/async", json=payload)
+    assert response.status_code == 200, "Response should be 200 OK"
+
+    task = response.json()
+
+    print(json.dumps(task, indent=2))
+
+    while task["task_status"] not in ("success", "failure"):
+        response = await async_client.get(f"{base_url}/status/poll/{task['task_id']}")
+        assert response.status_code == 200, "Response should be 200 OK"
+        task = response.json()
+        print(f"{task['task_status']=}")
+        print(f"{task['task_position']=}")
+
+        time.sleep(2)
+
+    assert task["task_status"] == "success"
+
+    result_resp = await async_client.get(f"{base_url}/result/{task['task_id']}")
+    assert result_resp.status_code == 200, "Response should be 200 OK"
+
+    # Check for zip file attachment
+    content_disposition = result_resp.headers.get("content-disposition")
+
+    with check:
+        assert content_disposition is not None, (
+            "Content-Disposition header should be present"
+        )
+    with check:
+        assert "attachment" in content_disposition, "Response should be an attachment"
+    with check:
+        assert 'filename="converted_docs.zip"' in content_disposition, (
+            "Attachment filename should be 'converted_docs.zip'"
+        )
+
+    content_type = result_resp.headers.get("content-type")
+    with check:
+        assert content_type == "application/zip", (
+            "Content-Type should be 'application/zip'"
+        )

tests/test_fastapi_endpoints.py

@@ -0,0 +1,156 @@
+import asyncio
+import json
+import os
+
+import pytest
+import pytest_asyncio
+from asgi_lifespan import LifespanManager
+from httpx import ASGITransport, AsyncClient
+from pytest_check import check
+
+from docling_serve.app import create_app
+
+
+@pytest.fixture(scope="session")
+def event_loop():
+    return asyncio.get_event_loop()
+
+
+@pytest_asyncio.fixture(scope="session")
+async def app():
+    app = create_app()
+
+    async with LifespanManager(app) as manager:
+        print("Launching lifespan of app.")
+        yield manager.app
+
+
+@pytest_asyncio.fixture(scope="session")
+async def client(app):
+    async with AsyncClient(
+        transport=ASGITransport(app=app), base_url="http://app.io"
+    ) as client:
+        print("Client is ready")
+        yield client
+
+
+@pytest.mark.asyncio
+async def test_health(client: AsyncClient):
+    response = await client.get("/health")
+    assert response.status_code == 200
+    assert response.json() == {"status": "ok"}
+
+
+@pytest.mark.asyncio
+async def test_convert_file(client: AsyncClient):
+    """Test convert single file to all outputs"""
+
+    endpoint = "/v1alpha/convert/file"
+    options = {
+        "from_formats": [
+            "docx",
+            "pptx",
+            "html",
+            "image",
+            "pdf",
+            "asciidoc",
+            "md",
+            "xlsx",
+        ],
+        "to_formats": ["md", "json", "html", "text", "doctags"],
+        "image_export_mode": "placeholder",
+        "ocr": True,
+        "force_ocr": False,
+        "ocr_engine": "easyocr",
+        "ocr_lang": ["en"],
+        "pdf_backend": "dlparse_v2",
+        "table_mode": "fast",
+        "abort_on_error": False,
+        "return_as_file": False,
+    }
+
+    current_dir = os.path.dirname(__file__)
+    file_path = os.path.join(current_dir, "2206.01062v1.pdf")
+
+    files = {
+        "files": ("2206.01062v1.pdf", open(file_path, "rb"), "application/pdf"),
+    }
+
+    response = await client.post(endpoint, files=files, data=options)
+    assert response.status_code == 200, "Response should be 200 OK"
+
+    data = response.json()
+
+    # Response content checks
+    # Helper function to safely slice strings
+    def safe_slice(value, length=100):
+        if isinstance(value, str):
+            return value[:length]
+        return str(value)  # Convert non-string values to string for debug purposes
+
+    # Document check
+    check.is_in(
+        "document",
+        data,
+        msg=f"Response should contain 'document' key. Received keys: {list(data.keys())}",
+    )
+    # MD check
+    check.is_in(
+        "md_content",
+        data.get("document", {}),
+        msg=f"Response should contain 'md_content' key. Received keys: {list(data.get('document', {}).keys())}",
+    )
+    if data.get("document", {}).get("md_content") is not None:
+        check.is_in(
+            "## DocLayNet: ",
+            data["document"]["md_content"],
+            msg=f"Markdown document should contain 'DocLayNet: '. Received: {safe_slice(data['document']['md_content'])}",
+        )
+    # JSON check
+    check.is_in(
+        "json_content",
+        data.get("document", {}),
+        msg=f"Response should contain 'json_content' key. Received keys: {list(data.get('document', {}).keys())}",
+    )
+    if data.get("document", {}).get("json_content") is not None:
+        check.is_in(
+            '{"schema_name": "DoclingDocument"',
+            json.dumps(data["document"]["json_content"]),
+            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>\n<head>",
+            data["document"]["html_content"],
+            msg=f"HTML document should contain '<!DOCTYPE html>\n<html>\n<head>'. Received: {safe_slice(data['document']['html_content'])}",
+        )
+    # Text check
+    check.is_in(
+        "text_content",
+        data.get("document", {}),
+        msg=f"Response should contain 'text_content' key. Received keys: {list(data.get('document', {}).keys())}",
+    )
+    if data.get("document", {}).get("text_content") is not None:
+        check.is_in(
+            "DocLayNet: A Large Human-Annotated Dataset",
+            data["document"]["text_content"],
+            msg=f"Text document should contain 'DocLayNet: A Large Human-Annotated Dataset'. Received: {safe_slice(data['document']['text_content'])}",
+        )
+    # DocTags check
+    check.is_in(
+        "doctags_content",
+        data.get("document", {}),
+        msg=f"Response should contain 'doctags_content' key. Received keys: {list(data.get('document', {}).keys())}",
+    )
+    if data.get("document", {}).get("doctags_content") is not None:
+        check.is_in(
+            "<doctag><page_header>",
+            data["document"]["doctags_content"],
+            msg=f"DocTags document should contain '<doctag><page_header>'. Received: {safe_slice(data['document']['doctags_content'])}",
+        )