mirror of
https://github.com/docling-project/docling-serve.git
synced 2025-11-29 16:43:24 +00:00
Compare commits
8 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5edc624fbf | ||
|
|
45f0f3c8f9 | ||
|
|
0595d31d5b | ||
|
|
f6b5f0e063 | ||
|
|
8b22a39141 | ||
|
|
d4eac053f9 | ||
|
|
fa1c5f04f3 | ||
|
|
ba61af2359 |
4
.github/workflows/job-image.yml
vendored
4
.github/workflows/job-image.yml
vendored
@@ -108,6 +108,7 @@ jobs:
|
||||
cache-to: type=gha,mode=max
|
||||
file: Containerfile
|
||||
build-args: ${{ inputs.build_args }}
|
||||
pull: true
|
||||
##
|
||||
## This stage runs after the build, so it leverages all build cache
|
||||
##
|
||||
@@ -226,7 +227,8 @@ jobs:
|
||||
cache-to: type=gha,mode=max
|
||||
file: Containerfile
|
||||
build-args: ${{ inputs.build_args }}
|
||||
pull: true
|
||||
|
||||
- name: Remove Local Docker Images
|
||||
- name: Remove local Docker images
|
||||
run: |
|
||||
docker image prune -af
|
||||
|
||||
@@ -34,6 +34,6 @@ repos:
|
||||
files: \.md$
|
||||
- repo: https://github.com/astral-sh/uv-pre-commit
|
||||
# uv version, https://github.com/astral-sh/uv-pre-commit/releases
|
||||
rev: 0.8.3
|
||||
rev: 0.8.19
|
||||
hooks:
|
||||
- id: uv-lock
|
||||
|
||||
26
CHANGELOG.md
26
CHANGELOG.md
@@ -1,3 +1,29 @@
|
||||
## [v1.6.0](https://github.com/docling-project/docling-serve/releases/tag/v1.6.0) - 2025-10-03
|
||||
|
||||
### Feature
|
||||
|
||||
* Pin new version of jobkit with granite-docling and connectors ([#391](https://github.com/docling-project/docling-serve/issues/391)) ([`0595d31`](https://github.com/docling-project/docling-serve/commit/0595d31d5b357553426215ca6771796a47e41324))
|
||||
|
||||
### Fix
|
||||
|
||||
* Update locked dependencies ([#392](https://github.com/docling-project/docling-serve/issues/392)) ([`45f0f3c`](https://github.com/docling-project/docling-serve/commit/45f0f3c8f95d418ac30e3744d27d02a63f9e4490))
|
||||
* **UI:** Allow both lowercase and uppercase extensions ([#386](https://github.com/docling-project/docling-serve/issues/386)) ([`8b22a39`](https://github.com/docling-project/docling-serve/commit/8b22a391418d22c1a4d706f880341f28702057b5))
|
||||
* Correctly raise HTTPException for Gateway Timeout ([#382](https://github.com/docling-project/docling-serve/issues/382)) ([`d4eac05`](https://github.com/docling-project/docling-serve/commit/d4eac053f9ce0a60f9070127335bdd56e193d7fa))
|
||||
* Pinning of higher version of dependencies to fix potential security issues ([#363](https://github.com/docling-project/docling-serve/issues/363)) ([`ba61af2`](https://github.com/docling-project/docling-serve/commit/ba61af23591eff200481aa2e532cf7d0701f0ea4))
|
||||
|
||||
### Documentation
|
||||
|
||||
* Fix docs for websocket breaking condition ([#390](https://github.com/docling-project/docling-serve/issues/390)) ([`f6b5f0e`](https://github.com/docling-project/docling-serve/commit/f6b5f0e06354d2db7d03d274b114499e3407dccf))
|
||||
|
||||
### Docling libraries included in this release:
|
||||
- docling 2.55.1
|
||||
- docling-core 2.48.4
|
||||
- docling-ibm-models 3.9.1
|
||||
- docling-jobkit 1.6.0
|
||||
- docling-mcp 1.3.2
|
||||
- docling-parse 4.5.0
|
||||
- docling-serve 1.6.0
|
||||
|
||||
## [v1.5.1](https://github.com/docling-project/docling-serve/releases/tag/v1.5.1) - 2025-09-17
|
||||
|
||||
### Fix
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
|
||||
|
||||
ARG UV_VERSION=0.8.3
|
||||
ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.8.19
|
||||
|
||||
ARG UV_SYNC_EXTRA_ARGS=""
|
||||
|
||||
@@ -25,7 +25,7 @@ RUN /usr/bin/fix-permissions /opt/app-root/src/.cache
|
||||
|
||||
ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/
|
||||
|
||||
FROM ghcr.io/astral-sh/uv:${UV_VERSION} AS uv_stage
|
||||
FROM ${UV_IMAGE} AS uv_stage
|
||||
|
||||
###################################################################################################
|
||||
# Docling layer #
|
||||
|
||||
@@ -46,7 +46,6 @@ from docling_jobkit.datamodel.s3_coords import S3Coordinates
|
||||
from docling_jobkit.datamodel.task import Task, TaskSource, TaskType
|
||||
from docling_jobkit.datamodel.task_targets import (
|
||||
InBodyTarget,
|
||||
TaskTarget,
|
||||
ZipTarget,
|
||||
)
|
||||
from docling_jobkit.orchestrators.base_orchestrator import (
|
||||
@@ -64,6 +63,7 @@ from docling_serve.datamodel.requests import (
|
||||
HttpSourceRequest,
|
||||
S3SourceRequest,
|
||||
TargetName,
|
||||
TargetRequest,
|
||||
make_request_model,
|
||||
)
|
||||
from docling_serve.datamodel.responses import (
|
||||
@@ -304,7 +304,7 @@ def create_app(): # noqa: C901
|
||||
convert_options: ConvertDocumentsRequestOptions,
|
||||
chunking_options: BaseChunkerOptions | None,
|
||||
chunking_export_options: ChunkingExportOptions | None,
|
||||
target: TaskTarget,
|
||||
target: TargetRequest,
|
||||
) -> Task:
|
||||
_log.info(f"Received {len(files)} files for processing.")
|
||||
|
||||
@@ -455,7 +455,7 @@ def create_app(): # noqa: C901
|
||||
|
||||
if not completed:
|
||||
# TODO: abort task!
|
||||
return HTTPException(
|
||||
raise HTTPException(
|
||||
status_code=504,
|
||||
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
|
||||
)
|
||||
@@ -511,7 +511,7 @@ def create_app(): # noqa: C901
|
||||
|
||||
if not completed:
|
||||
# TODO: abort task!
|
||||
return HTTPException(
|
||||
raise HTTPException(
|
||||
status_code=504,
|
||||
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
|
||||
)
|
||||
@@ -711,7 +711,7 @@ def create_app(): # noqa: C901
|
||||
|
||||
if not completed:
|
||||
# TODO: abort task!
|
||||
return HTTPException(
|
||||
raise HTTPException(
|
||||
status_code=504,
|
||||
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
|
||||
)
|
||||
@@ -793,7 +793,7 @@ def create_app(): # noqa: C901
|
||||
|
||||
if not completed:
|
||||
# TODO: abort task!
|
||||
return HTTPException(
|
||||
raise HTTPException(
|
||||
status_code=504,
|
||||
detail=f"Conversion is taking too long. The maximum wait time is configure as DOCLING_SERVE_MAX_SYNC_WAIT={docling_serve_settings.max_sync_wait}.",
|
||||
)
|
||||
|
||||
@@ -13,8 +13,8 @@ from docling_jobkit.datamodel.http_inputs import FileSource, HttpSource
|
||||
from docling_jobkit.datamodel.s3_coords import S3Coordinates
|
||||
from docling_jobkit.datamodel.task_targets import (
|
||||
InBodyTarget,
|
||||
PutTarget,
|
||||
S3Target,
|
||||
TaskTarget,
|
||||
ZipTarget,
|
||||
)
|
||||
|
||||
@@ -47,12 +47,17 @@ SourceRequestItem = Annotated[
|
||||
FileSourceRequest | HttpSourceRequest | S3SourceRequest, Field(discriminator="kind")
|
||||
]
|
||||
|
||||
TargetRequest = Annotated[
|
||||
InBodyTarget | ZipTarget | S3Target | PutTarget,
|
||||
Field(discriminator="kind"),
|
||||
]
|
||||
|
||||
|
||||
## Complete Source request
|
||||
class ConvertDocumentsRequest(BaseModel):
|
||||
options: ConvertDocumentsRequestOptions = ConvertDocumentsRequestOptions()
|
||||
sources: list[SourceRequestItem]
|
||||
target: TaskTarget = InBodyTarget()
|
||||
target: TargetRequest = InBodyTarget()
|
||||
|
||||
@model_validator(mode="after")
|
||||
def validate_s3_source_and_target(self) -> Self:
|
||||
@@ -94,7 +99,7 @@ class BaseChunkDocumentsRequest(BaseModel):
|
||||
),
|
||||
] = False
|
||||
target: Annotated[
|
||||
TaskTarget, Field(description="Specification for the type of output target.")
|
||||
TargetRequest, Field(description="Specification for the type of output target.")
|
||||
] = InBodyTarget()
|
||||
|
||||
|
||||
|
||||
@@ -570,14 +570,17 @@ with gr.Blocks(
|
||||
with gr.Tab("Convert File"):
|
||||
with gr.Row():
|
||||
with gr.Column(scale=4):
|
||||
raw_exts = itertools.chain.from_iterable(FormatToExtensions.values())
|
||||
file_input = gr.File(
|
||||
elem_id="file_input_zone",
|
||||
label="Upload File",
|
||||
file_types=[
|
||||
f".{v}"
|
||||
for v in itertools.chain.from_iterable(
|
||||
FormatToExtensions.values()
|
||||
)
|
||||
f".{v.lower()}"
|
||||
for v in raw_exts # lowercase
|
||||
]
|
||||
+ [
|
||||
f".{v.upper()}"
|
||||
for v in raw_exts # uppercase
|
||||
],
|
||||
file_count="multiple",
|
||||
scale=4,
|
||||
|
||||
@@ -433,7 +433,7 @@ with connect(uri) as websocket:
|
||||
payload = json.loads(message)
|
||||
if payload["message"] == "error":
|
||||
break
|
||||
if payload["message"] == "error" and payload["task"]["task_status"] in ("success", "failure"):
|
||||
if payload["message"] == "update" and payload["task"]["task_status"] in ("success", "failure"):
|
||||
break
|
||||
except:
|
||||
break
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "docling-serve"
|
||||
version = "1.5.1" # DO NOT EDIT, updated automatically
|
||||
version = "1.6.0" # DO NOT EDIT, updated automatically
|
||||
description = "Running Docling as a service"
|
||||
license = {text = "MIT"}
|
||||
authors = [
|
||||
@@ -35,7 +35,7 @@ requires-python = ">=3.10"
|
||||
dependencies = [
|
||||
"docling~=2.38",
|
||||
"docling-core>=2.45.0",
|
||||
"docling-jobkit[kfp,rq,vlm]>=1.5.0,<2.0.0",
|
||||
"docling-jobkit[kfp,rq,vlm]>=1.6.0,<2.0.0",
|
||||
"fastapi[standard]~=0.115",
|
||||
"httpx~=0.28",
|
||||
"pydantic~=2.10",
|
||||
@@ -50,7 +50,7 @@ dependencies = [
|
||||
|
||||
[project.optional-dependencies]
|
||||
ui = [
|
||||
"gradio~=5.23.2",
|
||||
"gradio>=5.23.2,<6.0.0",
|
||||
]
|
||||
tesserocr = [
|
||||
"tesserocr~=2.7"
|
||||
@@ -123,7 +123,8 @@ conflicts = [
|
||||
]
|
||||
environments = ["sys_platform != 'darwin' or platform_machine != 'x86_64'"]
|
||||
override-dependencies = [
|
||||
"urllib3~=2.0"
|
||||
"urllib3~=2.0",
|
||||
"xgrammar>=0.1.24"
|
||||
]
|
||||
|
||||
[tool.uv.sources]
|
||||
|
||||
Reference in New Issue
Block a user