mirror of
https://github.com/docling-project/docling-serve.git
synced 2025-11-29 08:33:50 +00:00
Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ff75bab21b | ||
|
|
7a0fabae07 | ||
|
|
9ffe49a359 | ||
|
|
68772bb6f0 | ||
|
|
20ec87a63a | ||
|
|
e30f458923 | ||
|
|
03e405638f | ||
|
|
fd8e40a008 | ||
|
|
422c402bab | ||
|
|
ea090288d3 | ||
|
|
07c48edd5d | ||
|
|
a212547d28 | ||
|
|
c76daac70c | ||
|
|
7994b19b9f | ||
|
|
ec57b528ed |
2
.github/SECURITY.md
vendored
2
.github/SECURITY.md
vendored
@@ -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).
|
||||
|
||||
6
.github/workflows/ci-images-dryrun.yml
vendored
6
.github/workflows/ci-images-dryrun.yml
vendored
@@ -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
|
||||
|
||||
2
.github/workflows/ci.yml
vendored
2
.github/workflows/ci.yml
vendored
@@ -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: ${{ github.event_name == 'push' || (github.event.pull_request.head.repo.full_name != 'docling-project/docling-serve' && github.event.pull_request.head.repo.full_name != 'docling-project/docling-serve') }}
|
||||
uses: ./.github/workflows/job-checks.yml
|
||||
permissions:
|
||||
packages: write
|
||||
|
||||
6
.github/workflows/images.yml
vendored
6
.github/workflows/images.yml
vendored
@@ -17,15 +17,15 @@ jobs:
|
||||
strategy:
|
||||
matrix:
|
||||
spec:
|
||||
- name: ds4sd/docling-serve
|
||||
- name: docling-project/docling-serve
|
||||
build_args: |
|
||||
UV_SYNC_EXTRA_ARGS=--no-extra cu124 --no-extra cpu
|
||||
platforms: linux/amd64, linux/arm64
|
||||
- name: ds4sd/docling-serve-cpu
|
||||
- name: docling-project/docling-serve-cpu
|
||||
build_args: |
|
||||
UV_SYNC_EXTRA_ARGS=--no-extra cu124
|
||||
platforms: linux/amd64, linux/arm64
|
||||
- name: ds4sd/docling-serve-cu124
|
||||
- name: docling-project/docling-serve-cu124
|
||||
build_args: |
|
||||
UV_SYNC_EXTRA_ARGS=--no-extra cpu
|
||||
platforms: linux/amd64
|
||||
|
||||
@@ -3,7 +3,7 @@ config:
|
||||
no-emphasis-as-header: false
|
||||
first-line-heading: false
|
||||
MD033:
|
||||
allowed_elements: ["details", "summary"]
|
||||
allowed_elements: ["details", "summary", "br", "a", "p", "img"]
|
||||
MD024:
|
||||
siblings_only: true
|
||||
globs:
|
||||
|
||||
@@ -5,10 +5,14 @@ repos:
|
||||
hooks:
|
||||
# Run the Ruff formatter.
|
||||
- id: ruff-format
|
||||
name: "Ruff formatter"
|
||||
args: [--config=pyproject.toml]
|
||||
files: '^(docling_serve|tests).*\.(py|ipynb)$'
|
||||
# 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
|
||||
|
||||
76
CHANGELOG.md
76
CHANGELOG.md
@@ -1,36 +1,66 @@
|
||||
## [v0.5.1](https://github.com/DS4SD/docling-serve/releases/tag/v0.5.1) - 2025-03-10
|
||||
|
||||
### Fix
|
||||
|
||||
* Submodules in wheels ([#85](https://github.com/DS4SD/docling-serve/issues/85)) ([`a92ad48`](https://github.com/DS4SD/docling-serve/commit/a92ad48b287bfcb134011dc0fc3f91ee04e067ee))
|
||||
|
||||
## [v0.5.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.5.0) - 2025-03-07
|
||||
## [v0.7.0](https://github.com/docling-project/docling-serve/releases/tag/v0.7.0) - 2025-03-31
|
||||
|
||||
### 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))
|
||||
* 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
|
||||
|
||||
* 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))
|
||||
* 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))
|
||||
|
||||
## [v0.4.0](https://github.com/DS4SD/docling-serve/releases/tag/v0.4.0) - 2025-02-26
|
||||
## [v0.6.0](https://github.com/docling-project/docling-serve/releases/tag/v0.6.0) - 2025-03-17
|
||||
|
||||
### 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))
|
||||
* 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
|
||||
|
||||
* 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))
|
||||
* 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))
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
###################################################################################################
|
||||
@@ -41,12 +38,16 @@ 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}
|
||||
|
||||
ARG MODELS_LIST="layout tableformer picture_classifier easyocr"
|
||||
|
||||
RUN echo "Downloading models..." && \
|
||||
HF_HUB_DOWNLOAD_TIMEOUT="90" \
|
||||
HF_HUB_ETAG_TIMEOUT="90" \
|
||||
|
||||
24
Makefile
24
Makefile
@@ -27,23 +27,23 @@ 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:main
|
||||
$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve:$(TAG) quay.io/docling-project/docling-serve:main
|
||||
|
||||
.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:main
|
||||
$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cpu:$(TAG) quay.io/docling-project/docling-serve-cpu:main
|
||||
|
||||
.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:main
|
||||
$(CMD_PREFIX) docker tag ghcr.io/docling-project/docling-serve-cu124:$(TAG) quay.io/docling-project/docling-serve-cu124:main
|
||||
|
||||
.PHONY: action-lint
|
||||
action-lint: .action-lint ## Lint GitHub Action workflows
|
||||
@@ -66,7 +66,7 @@ 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 +84,11 @@ 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
|
||||
|
||||
445
README.md
445
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>
|
||||

|
||||
|
||||
```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.
|
||||
|
||||

|
||||
|
||||
- An easy to use UI is available at the `/ui` endpoint.
|
||||
An easy to use UI is available at the `/ui` endpoint.
|
||||
|
||||

|
||||
|
||||

|
||||
|
||||
## 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}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
@@ -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,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -18,10 +18,15 @@ 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.convert import ConvertDocumentsOptions
|
||||
from docling_serve.datamodel.requests import (
|
||||
@@ -37,7 +42,7 @@ from docling_serve.datamodel.responses import (
|
||||
)
|
||||
from docling_serve.docling_conversion import (
|
||||
convert_documents,
|
||||
converters,
|
||||
get_converter,
|
||||
get_pdf_pipeline_opts,
|
||||
)
|
||||
from docling_serve.engines import get_orchestrator
|
||||
@@ -86,15 +91,8 @@ _log = logging.getLogger(__name__)
|
||||
@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,
|
||||
}
|
||||
)
|
||||
|
||||
converters[options_hash].initialize_pipeline(InputFormat.PDF)
|
||||
pdf_format_option = get_pdf_pipeline_opts(ConvertDocumentsOptions())
|
||||
get_converter(pdf_format_option)
|
||||
|
||||
orchestrator = get_orchestrator()
|
||||
|
||||
@@ -110,11 +108,6 @@ async def lifespan(app: FastAPI):
|
||||
except asyncio.CancelledError:
|
||||
_log.info("Queue processor cancelled.")
|
||||
|
||||
converters.clear()
|
||||
|
||||
# if WITH_UI:
|
||||
# gradio_ui.close()
|
||||
|
||||
|
||||
##################################
|
||||
# App creation and configuration #
|
||||
@@ -129,15 +122,25 @@ 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,
|
||||
@@ -170,6 +173,38 @@ 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",
|
||||
)
|
||||
|
||||
#############################
|
||||
# API Endpoints definitions #
|
||||
#############################
|
||||
@@ -177,9 +212,10 @@ 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")
|
||||
|
||||
@@ -4,9 +4,21 @@ from typing import Annotated, Optional
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
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,
|
||||
TableFormerMode,
|
||||
)
|
||||
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 ConvertDocumentsOptions(BaseModel):
|
||||
from_formats: Annotated[
|
||||
@@ -69,18 +81,17 @@ 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]],
|
||||
@@ -101,11 +112,11 @@ 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,
|
||||
@@ -172,3 +183,47 @@ 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
|
||||
|
||||
@@ -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 +10,3 @@ 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
|
||||
|
||||
19
docling_serve/datamodel/task.py
Normal file
19
docling_serve/datamodel/task.py
Normal file
@@ -0,0 +1,19 @@
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from docling_serve.datamodel.engines import TaskStatus
|
||||
from docling_serve.datamodel.requests import ConvertDocumentsRequest
|
||||
from docling_serve.datamodel.responses import ConvertDocumentResponse
|
||||
|
||||
|
||||
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
|
||||
@@ -2,6 +2,7 @@ import hashlib
|
||||
import json
|
||||
import logging
|
||||
from collections.abc import Iterable, Iterator
|
||||
from functools import lru_cache
|
||||
from pathlib import Path
|
||||
from typing import Any, Optional, Union
|
||||
|
||||
@@ -9,37 +10,30 @@ 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,
|
||||
PdfPipelineOptions,
|
||||
RapidOcrOptions,
|
||||
TableFormerMode,
|
||||
TesseractOcrOptions,
|
||||
)
|
||||
from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
|
||||
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 +58,50 @@ 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
|
||||
|
||||
|
||||
# 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)
|
||||
|
||||
|
||||
# Computes the PDF pipeline options and returns the PdfFormatOption and its hash
|
||||
def get_pdf_pipeline_opts( # noqa: C901
|
||||
def get_pdf_pipeline_opts(
|
||||
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}")
|
||||
) -> PdfFormatOption:
|
||||
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):
|
||||
@@ -120,6 +113,10 @@ def get_pdf_pipeline_opts( # noqa: C901
|
||||
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)
|
||||
@@ -133,6 +130,8 @@ def get_pdf_pipeline_opts( # noqa: C901
|
||||
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:
|
||||
@@ -168,11 +167,7 @@ def get_pdf_pipeline_opts( # noqa: C901
|
||||
backend=backend,
|
||||
)
|
||||
|
||||
serialized_data = _serialize_pdf_format_option(pdf_format_option)
|
||||
|
||||
options_hash = hashlib.sha1(serialized_data.encode()).digest()
|
||||
|
||||
return pdf_format_option, options_hash
|
||||
return pdf_format_option
|
||||
|
||||
|
||||
def convert_documents(
|
||||
@@ -180,18 +175,9 @@ 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,
|
||||
)
|
||||
|
||||
@@ -5,13 +5,14 @@ from typing import Optional
|
||||
|
||||
from fastapi import WebSocket
|
||||
|
||||
from docling_serve.datamodel.engines import Task, TaskStatus
|
||||
from docling_serve.datamodel.engines import TaskStatus
|
||||
from docling_serve.datamodel.requests import ConvertDocumentsRequest
|
||||
from docling_serve.datamodel.responses import (
|
||||
MessageKind,
|
||||
TaskStatusResponse,
|
||||
WebsocketMessage,
|
||||
)
|
||||
from docling_serve.datamodel.task import Task
|
||||
from docling_serve.engines.async_local.worker import AsyncLocalWorker
|
||||
from docling_serve.engines.base_orchestrator import BaseOrchestrator
|
||||
from docling_serve.settings import docling_serve_settings
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
from docling_serve.datamodel.engines import Task
|
||||
from docling_serve.datamodel.task import Task
|
||||
|
||||
|
||||
class BaseOrchestrator(ABC):
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
import importlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
@@ -9,14 +8,29 @@ import gradio as gr
|
||||
import requests
|
||||
|
||||
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@0.0.3"
|
||||
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>
|
||||
"""
|
||||
|
||||
#################
|
||||
@@ -96,7 +110,7 @@ file_output_path = None # Will be set when a new file is generated
|
||||
|
||||
|
||||
def health_check():
|
||||
response = requests.get(f"http://localhost:{int(os.getenv('PORT', '5001'))}/health")
|
||||
response = requests.get(f"http://localhost:{uvicorn_settings.port}/health")
|
||||
if response.status_code == 200:
|
||||
return "Healthy"
|
||||
return "Unhealthy"
|
||||
@@ -185,6 +199,10 @@ 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(",")],
|
||||
@@ -199,6 +217,10 @@ 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 (
|
||||
@@ -210,7 +232,7 @@ def process_url(
|
||||
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",
|
||||
f"http://localhost:{uvicorn_settings.port}/v1alpha/convert/source",
|
||||
json=parameters,
|
||||
)
|
||||
except Exception as e:
|
||||
@@ -237,6 +259,10 @@ 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] == "":
|
||||
logger.error("No files provided.")
|
||||
@@ -254,11 +280,15 @@ def process_file(
|
||||
"table_mode": table_mode,
|
||||
"abort_on_error": str(abort_on_error).lower(),
|
||||
"return_as_file": str(return_as_file).lower(),
|
||||
"do_code_enrichment": str(do_code_enrichment).lower(),
|
||||
"do_formula_enrichment": str(do_formula_enrichment).lower(),
|
||||
"do_picture_classification": str(do_picture_classification).lower(),
|
||||
"do_picture_description": str(do_picture_description).lower(),
|
||||
}
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"http://localhost:{int(os.getenv('PORT', '5001'))}/v1alpha/convert/file",
|
||||
f"http://localhost:{uvicorn_settings.port}/v1alpha/convert/file",
|
||||
files=files_data,
|
||||
data=parameters,
|
||||
)
|
||||
@@ -342,17 +372,21 @@ 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(
|
||||
@@ -478,6 +512,21 @@ with gr.Blocks(
|
||||
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
|
||||
)
|
||||
|
||||
# Document output
|
||||
with gr.Row(visible=False) as content_output:
|
||||
@@ -561,6 +610,10 @@ with gr.Blocks(
|
||||
table_mode,
|
||||
abort_on_error,
|
||||
return_as_file,
|
||||
do_code_enrichment,
|
||||
do_formula_enrichment,
|
||||
do_picture_classification,
|
||||
do_picture_description,
|
||||
],
|
||||
outputs=[
|
||||
output_markdown,
|
||||
@@ -630,6 +683,10 @@ with gr.Blocks(
|
||||
table_mode,
|
||||
abort_on_error,
|
||||
return_as_file,
|
||||
do_code_enrichment,
|
||||
do_formula_enrichment,
|
||||
do_picture_classification,
|
||||
do_picture_description,
|
||||
],
|
||||
outputs=[
|
||||
output_markdown,
|
||||
|
||||
@@ -16,6 +16,10 @@ 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
|
||||
|
||||
|
||||
@@ -29,6 +33,13 @@ class DoclingServeSettings(BaseSettings):
|
||||
|
||||
enable_ui: bool = False
|
||||
artifacts_path: Optional[Path] = None
|
||||
static_path: Optional[Path] = None
|
||||
options_cache_size: int = 2
|
||||
allow_external_plugins: bool = False
|
||||
|
||||
cors_origins: list[str] = ["*"]
|
||||
cors_methods: list[str] = ["*"]
|
||||
cors_headers: list[str] = ["*"]
|
||||
|
||||
eng_kind: AsyncEngine = AsyncEngine.LOCAL
|
||||
eng_loc_num_workers: int = 2
|
||||
|
||||
8
docs/README.md
Normal file
8
docs/README.md
Normal file
@@ -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)
|
||||
BIN
docs/assets/docling-serve-pic.png
Normal file
BIN
docs/assets/docling-serve-pic.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 504 KiB |
44
docs/configuration.md
Normal file
44
docs/configuration.md
Normal file
@@ -0,0 +1,44 @@
|
||||
# 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 |
|
||||
| `--enable-ui` | `DOCLING_SERVE_ENABLE_UI` | `false` | Enable the demonstrator UI. |
|
||||
| | `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. |
|
||||
209
docs/deploy-examples/docling-serve-oauth.yaml
Normal file
209
docs/deploy-examples/docling-serve-oauth.yaml
Normal file
@@ -0,0 +1,209 @@
|
||||
# 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"}}'
|
||||
---
|
||||
kind: Role
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
metadata:
|
||||
name: docling-serve-oauth
|
||||
labels:
|
||||
app: docling-serve
|
||||
component: docling-serve-api
|
||||
rules:
|
||||
- verbs:
|
||||
- create
|
||||
apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
- verbs:
|
||||
- create
|
||||
apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
---
|
||||
kind: RoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
metadata:
|
||||
name: docling-serve-oauth
|
||||
labels:
|
||||
app: docling-serve
|
||||
component: docling-serve-api
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: docling-serve
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: docling-serve-oauth
|
||||
---
|
||||
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: 500m
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 250m
|
||||
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: 2
|
||||
periodSeconds: 5
|
||||
successThreshold: 1
|
||||
failureThreshold: 3
|
||||
env:
|
||||
- name: DOCLING_SERVE_ENABLE_UI
|
||||
value: 'true'
|
||||
- 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:dev-ssl'
|
||||
- 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":"$(NAMESPACE)","resource":"routes","resourceName":"docling-serve","verb":"get","resourceAPIGroup":"route.openshift.io"}'
|
||||
- '--skip-auth-regex=''(^/health|^/docs)'''
|
||||
volumes:
|
||||
- name: proxy-tls
|
||||
secret:
|
||||
secretName: docling-serve-tls
|
||||
defaultMode: 420
|
||||
40
docs/deployment.md
Normal file
40
docs/deployment.md
Normal file
@@ -0,0 +1,40 @@
|
||||
# Deployment
|
||||
|
||||
## OpenShift
|
||||
|
||||
### Secure deployment with `oauth-proxy`
|
||||
|
||||
Manifest example: [docling-serve-oauth.yaml](./deploy-examples/docling-serve-oauth.yaml)
|
||||
|
||||
This deployment has the following features:
|
||||
|
||||
- TLS encryption between all components (using the cluster-internal CA authority).
|
||||
- Authentication via a secure `oauth-proxy` sidecar.
|
||||
- Expose the service using a secure OpenShift `Route`
|
||||
|
||||
Install the app with:
|
||||
|
||||
```sh
|
||||
kubectl apply -f docs/deploy-examples/docling-serve-oauth.yaml
|
||||
```
|
||||
|
||||
For using the API:
|
||||
|
||||
```sh
|
||||
# Retrieve the endpoint
|
||||
DOCLING_NAME=docling-serve
|
||||
DOCLING_ROUTE="https://$(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"}]
|
||||
}'
|
||||
```
|
||||
57
docs/development.md
Normal file
57
docs/development.md
Normal file
@@ -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
|
||||
```
|
||||
279
docs/usage.md
Normal file
279
docs/usage.md
Normal file
@@ -0,0 +1,279 @@
|
||||
# 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_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.
|
||||
|
||||
## 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>
|
||||
|
||||
## 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
|
||||
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "docling-serve"
|
||||
version = "0.5.1" # DO NOT EDIT, updated automatically
|
||||
version = "0.7.0" # DO NOT EDIT, updated automatically
|
||||
description = "Running Docling as a service"
|
||||
license = {text = "MIT"}
|
||||
authors = [
|
||||
@@ -30,7 +30,7 @@ classifiers = [
|
||||
]
|
||||
requires-python = ">=3.10"
|
||||
dependencies = [
|
||||
"docling~=2.25.1",
|
||||
"docling~=2.28",
|
||||
"fastapi[standard]~=0.115",
|
||||
"httpx~=0.28",
|
||||
"pydantic~=2.10",
|
||||
@@ -109,11 +109,11 @@ namespaces = true
|
||||
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"
|
||||
|
||||
74
uv.lock
generated
74
uv.lock
generated
@@ -378,7 +378,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "docling"
|
||||
version = "2.25.1"
|
||||
version = "2.28.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "beautifulsoup4" },
|
||||
@@ -394,8 +394,10 @@ dependencies = [
|
||||
{ name = "openpyxl" },
|
||||
{ name = "pandas" },
|
||||
{ name = "pillow" },
|
||||
{ name = "pluggy" },
|
||||
{ name = "pydantic" },
|
||||
{ name = "pydantic-settings" },
|
||||
{ name = "pylatexenc" },
|
||||
{ name = "pypdfium2" },
|
||||
{ name = "python-docx" },
|
||||
{ name = "python-pptx" },
|
||||
@@ -405,14 +407,14 @@ dependencies = [
|
||||
{ name = "tqdm" },
|
||||
{ name = "typer" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/f9/88/b6d782d2cd7ed602d2bae1a01e87a6347a37295ad450d86159cc7c252290/docling-2.25.1.tar.gz", hash = "sha256:ba2fce77659f4ccf1c8a696531ea9f17253215dbebfac6536012bbc6d1c29ce8", size = 112676 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/96/8a/4b342316cf6f1bd56f30da0595eaf7b2eb8899297653e97eb6c6e01b6cc4/docling-2.28.0.tar.gz", hash = "sha256:26fe35a161039b3b33939358918e25f96e902121690e1791f3e324c6332d2f2f", size = 121741 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/2a/c1/6c58516672f0f60c432ae331391b6548e4fdcb7b6a6dcd7725605284dcf7/docling-2.25.1-py3-none-any.whl", hash = "sha256:92318591342fc50781134fc553c6c57b703ce43e8095a80d59ed02206d0f560c", size = 145677 },
|
||||
{ url = "https://files.pythonhosted.org/packages/d3/2c/c14d03c1631dbe366cb539cf7f3bef0df676594bfb244ae709a25b248ff2/docling-2.28.0-py3-none-any.whl", hash = "sha256:5a2b87788c4c969016f38c8f288599c942b4b36687fff43e7e49ef2419b038d1", size = 159615 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "docling-core"
|
||||
version = "2.19.1"
|
||||
version = "2.23.3"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "jsonref" },
|
||||
@@ -426,9 +428,9 @@ dependencies = [
|
||||
{ name = "typer" },
|
||||
{ name = "typing-extensions" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/a3/e5/ddc7f15e28165929cff022f12755023cd29f0273b5008cc4651191a38bc1/docling_core-2.19.1.tar.gz", hash = "sha256:e2769b816c669cdf27024dd3b219d3ecaf2161691dd5e8e5e8ce439557ea0928", size = 75441 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/89/e7/dae1d9e2be58fc42a60680ec463dba7df87fb84219e67724054ad69e66e2/docling_core-2.23.3.tar.gz", hash = "sha256:a64ce41e0881c06962a2b3ec80e0665f84de0809dedf1bf84f3a14b75dd665c4", size = 92751 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/ed/59d4aab03446fa037de532225096162cb967f90d97c163741fd824f76b98/docling_core-2.19.1-py3-none-any.whl", hash = "sha256:ca7bd4dacd75611c5ea4f205192b71a8f22205e615eff1a16aac7082644d3b2e", size = 95587 },
|
||||
{ url = "https://files.pythonhosted.org/packages/3f/1c/c0c9e90de6b1d697d274be7e4c1c6c52f8e169e367e9b2fbf6bc1b6aad3b/docling_core-2.23.3-py3-none-any.whl", hash = "sha256:a2166ffc41f8fdf6fdb99b33da6c7146eccf6382712ea92e95772604fb5af5e5", size = 115889 },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
@@ -468,7 +470,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "docling-parse"
|
||||
version = "3.4.0"
|
||||
version = "4.0.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "docling-core" },
|
||||
@@ -477,34 +479,34 @@ dependencies = [
|
||||
{ name = "pywin32", marker = "sys_platform == 'win32' or (extra == 'extra-13-docling-serve-cpu' and extra == 'extra-13-docling-serve-cu124')" },
|
||||
{ name = "tabulate" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/b9/86/f927c8455c985f10aedf1e5f28afdf89fce61c8e927046c2127a09777fa5/docling_parse-3.4.0.tar.gz", hash = "sha256:36cdd17bcc4a833b5c9af9ae3dc461ed18a975c1b084ccfd19a9d9cde4f66e14", size = 36234965 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/1c/49/c722b719882442f909d254c33ed8d0ff87e72bee6dc50e0dc3ba9a9a7519/docling_parse-4.0.0.tar.gz", hash = "sha256:5be0ba4e0098524f116743e6b709f29fe273e441e61923c3a262e054643c5ee6", size = 36249833 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/51/ad/52d9ace2d46c2a5a31ea77ab38857a447a224f7b2878f6042d17b06c6bc9/docling_parse-3.4.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:96e95e63ab722dfe5340fcb04d0e07bd1c0a0ba2f62e93c91ac26dda0a312a44", size = 14711344 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0e/01/3bd99e200e63d9c238d4abbd3dd982ec347fc2ee7e2e91e8bdb0ee72dc17/docling_parse-3.4.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:f9e14a7a0b92526d4dfd3f390f3d7e075f59d14d6b8a0a564fbc26299e56cd47", size = 14588249 },
|
||||
{ url = "https://files.pythonhosted.org/packages/89/15/f41568765d908ad2cb5dff32d42044cb5a03753744d679dd7d9f5162fcb4/docling_parse-3.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdef1d51291e841e5b6a32689a39a9f35986389f863b415eaa1790b29d021101", size = 15030528 },
|
||||
{ url = "https://files.pythonhosted.org/packages/48/9c/35fd6f6ab719553920c85c4fc0246f60c4a2f7a533d7ecd394f8c3a37083/docling_parse-3.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68652610d6c34adc684dbaa77b5d596b25d004912a78e85ec4ae57910bf7086f", size = 15101143 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6d/cb/dd9ba1862162ac437137920d834d6a2256f5d5c9ea0775d710b854c0ec54/docling_parse-3.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:daad07fe93f306d8e2378acb24ef2fa68535ccdb960a1b99d6b36ab8c299fef1", size = 15893428 },
|
||||
{ url = "https://files.pythonhosted.org/packages/d1/ac/c136192d1784ee8fab3c6830593e3a87bf1016509ddd7a2764eac05ba771/docling_parse-3.4.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:6f30c5fd3c04bd3d1a7d06baeae2e5c3adbebc284071a9a52b0150bcd4917a3d", size = 14712548 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f1/99/d538dcf7ae680758a7a7d02bd81f8006e65a6d3e3d025e6e6080156e7d39/docling_parse-3.4.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:2c3664e4c8980dc44e0d026b1b01fbc94f0dac9adf7be835071d4a761977c36d", size = 14590167 },
|
||||
{ url = "https://files.pythonhosted.org/packages/cd/ce/1de7ae0ff12ba4d42521b94966519f1002188e167e7381a8cc8d91c70020/docling_parse-3.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3febf7515453d18df03c275356db2bb5b0618ba9fc033aba05d58318a9846b1a", size = 15031706 },
|
||||
{ url = "https://files.pythonhosted.org/packages/79/3f/637dffc7f6dd801f5c75c4966a1214fb861d6c8a5a9bc20a6df059c94e4b/docling_parse-3.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75aeb038bb7f6400ecde99cf6c4ef35867c528ac21676071a822ed72d0653149", size = 15102430 },
|
||||
{ url = "https://files.pythonhosted.org/packages/9b/e7/947e71491bf3d6fbe4447153abd795f557dc3d8a85231517da8979bf1d2c/docling_parse-3.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:8d20e3584022542448c21ed0ac868b2457ae35211cea63ed20142e375549e633", size = 15894464 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7b/3a/08bd1f4812c111bd2445efaf966ca9ae25f201ac9f4acee7698764ff21a6/docling_parse-3.4.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:ddfe2bd730ed08363f25954a0480da021e6e6bdb175276643cc2913a6bbd98e2", size = 14713125 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e6/aa/5aaf003f1c9828e62356306ae100f78cf9014a5910f11e9cb0de6beec79a/docling_parse-3.4.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:faf8ba9eaab8c17ea72516be5d440f754fcca27f37488dcf126a0f3ac3a63058", size = 14589373 },
|
||||
{ url = "https://files.pythonhosted.org/packages/af/e5/6dfc59a2aa1adedd43775b48a573e61722e3370d7e435c2fede2f11cdedd/docling_parse-3.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9eb5e7e50b3057690d0d4fa651363cafd7735bb952378dd8a4ca6c7d359507db", size = 15030339 },
|
||||
{ url = "https://files.pythonhosted.org/packages/24/08/40e4cf6d1e795b6e713d761331ee5bc1f3bb908ea5e2897f1e57fb220493/docling_parse-3.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:452334b387e2c699f69acf37a4ea4ae7097d062a2dd1980c573b73051c031158", size = 15101855 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7c/f4/e5f336bee750f149eb8d85e880569a67cf826aedc3b1f182f47863746a38/docling_parse-3.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:1ba00147ccb0a1dc10cdf58645e67f4ee895c6920bc583bc6f25d27cd562bfed", size = 15894431 },
|
||||
{ url = "https://files.pythonhosted.org/packages/8b/bb/8442795663aa32259b4789002a25966a0a46129bb5f7877c4efaa7cfde24/docling_parse-3.4.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:2b22a33a2d2f3616a7ac0f4b2f2ba6099f8a5dc6fa328be0f17c9c506455d7c1", size = 14713233 },
|
||||
{ url = "https://files.pythonhosted.org/packages/55/1c/d8ccd619ec3105bc8b1c933540f2344e3adb8b73f7bf65e3d8b6867e258d/docling_parse-3.4.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:0dd2440a94d555f98b702e88bfe7cc5a585d9191f4ea93884b02e286e7af3a06", size = 14589505 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/6d/c1f798eb3cf942fa34e9d9cbd896f0ad2cb457ce49ff73f53a11ba16cf4e/docling_parse-3.4.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f5828744a0e33136e09e8c61ca0b2c0ead8f76595f2e0955beaac16adce51f5", size = 15030504 },
|
||||
{ url = "https://files.pythonhosted.org/packages/20/a5/9f024aaf9ae30ab2e362b753f43962a097709befa726a1362b0c29740db9/docling_parse-3.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26fff6e36809d17ff855532f985df3738ada8d86a9fc746049ea6e6524d5e0a2", size = 15102307 },
|
||||
{ url = "https://files.pythonhosted.org/packages/59/1f/ebb8f766ed0b9aa10643f71e03cca422bca4eef2df539f35b0dfe0e66dda/docling_parse-3.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:13fc442f64171280db98dc4507274ffa0a65bac94eecbcc60c3cbf41f433b556", size = 15894198 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/24/e81e2b523984f6e25f5e5a5c117df3d5971d3e83c517d6f8371bf73f4a92/docling_parse-3.4.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:930f5a5d78404de573c0ba302d313b6647f1e86714766e5a1cdc09af014ca111", size = 17696437 },
|
||||
{ url = "https://files.pythonhosted.org/packages/ad/6f/95aa63b6a90f3856098c1279df2d4a8765e4918e3b8992dbc8d3afd34a34/docling_parse-4.0.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:6de7fa8ec4919f604c9a02a3fa8ca0e13a3a8e3c0652adc41848616b737925d9", size = 14705811 },
|
||||
{ url = "https://files.pythonhosted.org/packages/95/88/3f1c565f9ccced7dbac2eeabc770a94b5a878396b82845fde1aa009ba1d7/docling_parse-4.0.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:82704280ab086a84a30d9ec9def6cd96b733aefc6973546b2101d09eed7a958e", size = 14582832 },
|
||||
{ url = "https://files.pythonhosted.org/packages/2e/bc/12cc8fa558223e8cf13c255a8ced9e0a7f891fe0d4befeb91f00d87b5e12/docling_parse-4.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f51ec645978d75e7cf232fa7c571ebf164a5bdf418588c663f9b3c062df6ba72", size = 15031715 },
|
||||
{ url = "https://files.pythonhosted.org/packages/46/ca/8cf0c729a41ec527efdfc044164c553b38d1091c29f4217f32f627dce3c6/docling_parse-4.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d5da855f35303f9229198891da550e3c1e1f4025e52ab8c0303d345669ff46f", size = 15102096 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/cd/72e934f791fdb5dff7782d5847590644c8c2853020540c5550bbbde9ef58/docling_parse-4.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:ba36cb329aadb306cc25901305d49fe6d2ed9e93e9dc993b4baf13fcc90a98e1", size = 15887834 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/26/8d7d860f7801b291f0ea3bd00c19ae975955670b0b6ffb4e79a71fc7d810/docling_parse-4.0.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:9b7afbf09945b4d9e3ddb9c24a13d7b9f987cf32d5c9d68532ceb63fb26697df", size = 14707010 },
|
||||
{ url = "https://files.pythonhosted.org/packages/17/41/55195ee0026553d806ed0f4ce191f31905f3e8b89498ad18702bf806dd69/docling_parse-4.0.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:6daaec89c5045e968785a225b9b5a42b36dfe6b5a4437995e2d34e1595e2c162", size = 14584599 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e1/e2/22b152b41a43ea96da8df0646d1a4109e99fa752e671aed2dbfad2f4938d/docling_parse-4.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:93e638ef2ad36e9e4a8ef881073696467e6699bf206e5a416de4abaaf531b0e1", size = 15032938 },
|
||||
{ url = "https://files.pythonhosted.org/packages/be/38/e8d1509ee97de600c9948d98f7f3065788d3ed0443571eb37660eda3f784/docling_parse-4.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87246eb0d259202a7f093336f17235cb1fffb67e82b41dbc0e88f9c05b08014e", size = 15103407 },
|
||||
{ url = "https://files.pythonhosted.org/packages/83/8b/aa17424464e01cb03c16f8ac5fd215866204427aa6fcf2d6f400a7c70ea8/docling_parse-4.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:0ae44b913b010994c3e36869e5fc9dad252a7dc7434225790928075c8b5a7f6c", size = 15888873 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b1/9e/59f33d23052393ccd80566b48dcce391dcaa0bb14cf6cbd0234d1f878f34/docling_parse-4.0.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:ed6d8ac29c1014ed7a126d782b6bc963c9a9c09f41224fa90f9a8b45bf3191f9", size = 14707578 },
|
||||
{ url = "https://files.pythonhosted.org/packages/88/a3/ff04496290f242cb6b6679c79dde5f2dd37ba8332c60234787caacc154de/docling_parse-4.0.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:4a2dd46cee8e54f3aa511dbf552ef5f9f422944c54de73888ee55b2c4a6e10b9", size = 14583898 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fc/45/461992f6d866ecd19f6b00004d6ced7063561733cabc040e3079ed44b730/docling_parse-4.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:722fbd63f7f28e8a49fa2cd92d1571290f6c5295b86c7406b7c20a6c6e8b3975", size = 15031532 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6f/08/b87ef326fa7b97b91476d9e79c241fba55b3825a7d128e3cc7ee328e37c6/docling_parse-4.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc155767b51a23f5bfd5abaabaf8c4a57777aa0277c813e13b9f6c43532964bd", size = 15102813 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0c/7c/540a6cec0e06826d978ed363c7b3e042c8226ffb61c92a1bb70f649405d8/docling_parse-4.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:e45ab31fffe4ae571bd2ecc9e0a9d5665a1486463396924160add84828d2a7e7", size = 15888837 },
|
||||
{ url = "https://files.pythonhosted.org/packages/ed/e3/902a70c90037fedde03d4656bbd0ae9870cbab9738ccae62139f67722d71/docling_parse-4.0.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:d93fd3cec032e5b7f6385f7a021e228c52eb381f28fc037224708aeaad487d8b", size = 14707694 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/86/348563fb71079ec79b38961cbc9cdafbe18e14a24c727e96c11d011f39be/docling_parse-4.0.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:d9f64847cd7e9a7a34a3d5a14f0827022ed3b7f50f39d5126ef003c55d574ba3", size = 14584061 },
|
||||
{ url = "https://files.pythonhosted.org/packages/39/f1/dcf8a7530ae4966f22c1078a683e92a5e174fb2eff9d5ce78e95151bbf9a/docling_parse-4.0.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a6ac283f08680dfde568b5629ab94830cab32795d74086553e755460b6879901", size = 15031728 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/76/bdf33b0c3a555405d150f1a29cacb2c1df2875b4f70e62e4432e06adfa8c/docling_parse-4.0.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97eca28220dc5075099e01f2cb7a3e9005b9951dee0ca0eb743e298be7284279", size = 15103250 },
|
||||
{ url = "https://files.pythonhosted.org/packages/8d/db/c40db2c555860a86da67453cca1aa842d434a8f28693e4c96ef5f85936c0/docling_parse-4.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:6019288cfe25a97993c2aab453386fc3e366d7761637e682b25915ba2c856cc4", size = 15888608 },
|
||||
{ url = "https://files.pythonhosted.org/packages/4c/8d/b6b5a557d75e4313d82ab508e4bf0c645805bef2474c6e0e1164661b8cc0/docling_parse-4.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:30c0c1b33c0a0aeb6897537f7d8fa09ed5a26f05685b18a2d27c73a789343679", size = 17690840 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "docling-serve"
|
||||
version = "0.5.1"
|
||||
version = "0.7.0"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "docling" },
|
||||
@@ -553,7 +555,7 @@ dev = [
|
||||
|
||||
[package.metadata]
|
||||
requires-dist = [
|
||||
{ name = "docling", specifier = "~=2.25.1" },
|
||||
{ name = "docling", specifier = "~=2.28" },
|
||||
{ name = "fastapi", extras = ["standard"], specifier = "~=0.115" },
|
||||
{ name = "gradio", marker = "extra == 'ui'", specifier = "~=5.9" },
|
||||
{ name = "httpx", specifier = "~=0.28" },
|
||||
@@ -2133,6 +2135,12 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/0b/9fcc47d19c48b59121088dd6da2488a49d5f72dacf8262e2790a1d2c7d15/pygments-2.19.1-py3-none-any.whl", hash = "sha256:9ea1544ad55cecf4b8242fab6dd35a93bbce657034b0611ee383099054ab6d8c", size = 1225293 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pylatexenc"
|
||||
version = "2.10"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/5d/ab/34ec41718af73c00119d0351b7a2531d2ebddb51833a36448fc7b862be60/pylatexenc-2.10.tar.gz", hash = "sha256:3dd8fd84eb46dc30bee1e23eaab8d8fb5a7f507347b23e5f38ad9675c84f40d3", size = 162597 }
|
||||
|
||||
[[package]]
|
||||
name = "pypdfium2"
|
||||
version = "4.30.1"
|
||||
@@ -3457,6 +3465,10 @@ dependencies = [
|
||||
{ name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "(extra == 'extra-13-docling-serve-cpu' and extra == 'extra-13-docling-serve-cu124') or (extra != 'extra-13-docling-serve-cpu' and extra != 'extra-13-docling-serve-cu124')" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/a9/20/72eb0b5b08fa293f20fc41c374e37cf899f0033076f0144d2cdc48f9faee/torchvision-0.21.0-1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:5568c5a1ff1b2ec33127b629403adb530fab81378d9018ca4ed6508293f76e2b", size = 2327643 },
|
||||
{ url = "https://files.pythonhosted.org/packages/4e/3d/b7241abfa3e6651c6e00796f5de2bd1ce4d500bf5159bcbfeea47e711b93/torchvision-0.21.0-1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ff96666b94a55e802ea6796cabe788541719e6f4905fc59c380fed3517b6a64d", size = 2329320 },
|
||||
{ url = "https://files.pythonhosted.org/packages/52/5b/76ca113a853b19c7b1da761f8a72cb6429b3bd0bf932537d8df4657f47c3/torchvision-0.21.0-1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:ffa2a16499508fe6798323e455f312c7c55f2a88901c9a7c0fb1efa86cf7e327", size = 2329878 },
|
||||
{ url = "https://files.pythonhosted.org/packages/4e/fe/5e193353706dab96fe73ae100d5a633ff635ce310e0d92f3bc2958d075b1/torchvision-0.21.0-1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:7e9e9afa150e40cd2a8f0701c43cb82a8d724f512896455c0918b987f94b84a4", size = 2280711 },
|
||||
{ url = "https://files.pythonhosted.org/packages/8e/0d/143bd264876fad17c82096b6c2d433f1ac9b29cdc69ee45023096976ee3d/torchvision-0.21.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:044ea420b8c6c3162a234cada8e2025b9076fa82504758cd11ec5d0f8cd9fa37", size = 1784140 },
|
||||
{ url = "https://files.pythonhosted.org/packages/5e/44/32e2d2d174391374d5ff3c4691b802e8efda9ae27ab9062eca2255b006af/torchvision-0.21.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:b0c0b264b89ab572888244f2e0bad5b7eaf5b696068fc0b93e96f7c3c198953f", size = 7237187 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0e/6b/4fca9373eda42c1b04096758306b7bd55f7d8f78ba273446490855a0f25d/torchvision-0.21.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:54815e0a56dde95cc6ec952577f67e0dc151eadd928e8d9f6a7f821d69a4a734", size = 14699067 },
|
||||
|
||||
Reference in New Issue
Block a user