mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-30 14:04:27 +00:00
Merge branch 'docling-project:main' into main
This commit is contained in:
Ulan Yisaev
GitHub
commit
2b6fd251a7
18
CHANGELOG.md
18
CHANGELOG.md
@ -1,3 +1,21 @@
|
||||
## [v2.28.0](https://github.com/docling-project/docling/releases/tag/v2.28.0) - 2025-03-19
|
||||
|
||||
### Feature
|
||||
|
||||
* **SmolDocling:** Support MLX acceleration in VLM pipeline ([#1199](https://github.com/docling-project/docling/issues/1199)) ([`1c26769`](https://github.com/docling-project/docling/commit/1c26769785bcd17c0b8b621c5182ad81134d3915))
|
||||
* Add PPTX notes slides ([#474](https://github.com/docling-project/docling/issues/474)) ([`b454aa1`](https://github.com/docling-project/docling/commit/b454aa1551b891644ce4028ed2d7ec8f82c167ab))
|
||||
* Updated vlm pipeline (with latest changes from docling-core) ([#1158](https://github.com/docling-project/docling/issues/1158)) ([`2f72167`](https://github.com/docling-project/docling/commit/2f72167ff6421424dea4d93018b0d43af16ec153))
|
||||
|
||||
### Fix
|
||||
|
||||
* Determine correct page size in DoclingParseV4Backend ([#1196](https://github.com/docling-project/docling/issues/1196)) ([`f5adfb9`](https://github.com/docling-project/docling/commit/f5adfb9724aae1207f23e21d74033f331e6e1ffb))
|
||||
* **msword:** Fixing function return in equations handling ([#1194](https://github.com/docling-project/docling/issues/1194)) ([`0b707d0`](https://github.com/docling-project/docling/commit/0b707d0882f5be42505871799387d0b1882bffbf))
|
||||
|
||||
### Documentation
|
||||
|
||||
* Linux Foundation AI & Data ([#1183](https://github.com/docling-project/docling/issues/1183)) ([`1d680b0`](https://github.com/docling-project/docling/commit/1d680b0a321d95fc6bd65b7bb4d5e15005a0250a))
|
||||
* Move apify to docs ([#1182](https://github.com/docling-project/docling/issues/1182)) ([`54a78c3`](https://github.com/docling-project/docling/commit/54a78c307de833b93f9b84cf1f8ed6dace8573cb))
|
||||
|
||||
## [v2.27.0](https://github.com/docling-project/docling/releases/tag/v2.27.0) - 2025-03-18
|
||||
|
||||
### Feature
|
||||
|
||||
20
README.md
20
README.md
@ -35,7 +35,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
|
||||
* 🔒 Local execution capabilities for sensitive data and air-gapped environments
|
||||
* 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
|
||||
* 🔍 Extensive OCR support for scanned PDFs and images
|
||||
* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
|
||||
* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
|
||||
* 💻 Simple and convenient CLI
|
||||
|
||||
### Coming soon
|
||||
@ -57,7 +57,7 @@ More [detailed installation instructions](https://docling-project.github.io/docl
|
||||
|
||||
## Getting started
|
||||
|
||||
To convert individual documents, use `convert()`, for example:
|
||||
To convert individual documents with python, use `convert()`, for example:
|
||||
|
||||
```python
|
||||
from docling.document_converter import DocumentConverter
|
||||
@ -71,6 +71,22 @@ print(result.document.export_to_markdown()) # output: "## Docling Technical Rep
|
||||
More [advanced usage options](https://docling-project.github.io/docling/usage/) are available in
|
||||
the docs.
|
||||
|
||||
## CLI
|
||||
|
||||
Docling has a built-in CLI to run conversions.
|
||||
|
||||
```bash
|
||||
docling https://arxiv.org/pdf/2206.01062
|
||||
```
|
||||
|
||||
You can also use 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI:
|
||||
```bash
|
||||
docling --pipeline vlm --vlm-model smoldocling https://arxiv.org/pdf/2206.01062
|
||||
```
|
||||
This will use MLX acceleration on supported Apple Silicon hardware.
|
||||
|
||||
Read more [here](https://docling-project.github.io/docling/usage/)
|
||||
|
||||
## Documentation
|
||||
|
||||
Check out Docling's [documentation](https://docling-project.github.io/docling/), for details on
|
||||
|
||||
@ -16,6 +16,7 @@ from docling_core.types.doc import (
|
||||
TableCell,
|
||||
TableData,
|
||||
)
|
||||
from docling_core.types.doc.document import ContentLayer
|
||||
from PIL import Image, UnidentifiedImageError
|
||||
from pptx import Presentation
|
||||
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
|
||||
@ -421,4 +422,21 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
for shape in slide.shapes:
|
||||
handle_shapes(shape, parent_slide, slide_ind, doc, slide_size)
|
||||
|
||||
# Handle notes slide
|
||||
if slide.has_notes_slide:
|
||||
notes_slide = slide.notes_slide
|
||||
notes_text = notes_slide.notes_text_frame.text.strip()
|
||||
if notes_text:
|
||||
bbox = BoundingBox(l=0, t=0, r=0, b=0)
|
||||
prov = ProvenanceItem(
|
||||
page_no=slide_ind + 1, charspan=[0, len(notes_text)], bbox=bbox
|
||||
)
|
||||
doc.add_text(
|
||||
label=DocItemLabel.TEXT,
|
||||
parent=parent_slide,
|
||||
text=notes_text,
|
||||
prov=prov,
|
||||
content_layer=ContentLayer.FURNITURE,
|
||||
)
|
||||
|
||||
return doc
|
||||
|
||||
@ -32,13 +32,21 @@ from docling.datamodel.pipeline_options import (
|
||||
AcceleratorOptions,
|
||||
EasyOcrOptions,
|
||||
OcrOptions,
|
||||
PaginatedPipelineOptions,
|
||||
PdfBackend,
|
||||
PdfPipeline,
|
||||
PdfPipelineOptions,
|
||||
TableFormerMode,
|
||||
VlmModelType,
|
||||
VlmPipelineOptions,
|
||||
granite_vision_vlm_conversion_options,
|
||||
smoldocling_vlm_conversion_options,
|
||||
smoldocling_vlm_mlx_conversion_options,
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
|
||||
from docling.models.factories import get_ocr_factory
|
||||
from docling.pipeline.vlm_pipeline import VlmPipeline
|
||||
|
||||
warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")
|
||||
warnings.filterwarnings(action="ignore", category=FutureWarning, module="easyocr")
|
||||
@ -200,6 +208,14 @@ def convert(
|
||||
help="Image export mode for the document (only in case of JSON, Markdown or HTML). With `placeholder`, only the position of the image is marked in the output. In `embedded` mode, the image is embedded as base64 encoded string. In `referenced` mode, the image is exported in PNG format and referenced from the main exported document.",
|
||||
),
|
||||
] = ImageRefMode.EMBEDDED,
|
||||
pipeline: Annotated[
|
||||
PdfPipeline,
|
||||
typer.Option(..., help="Choose the pipeline to process PDF or image files."),
|
||||
] = PdfPipeline.STANDARD,
|
||||
vlm_model: Annotated[
|
||||
VlmModelType,
|
||||
typer.Option(..., help="Choose the VLM model to use with PDF or image files."),
|
||||
] = VlmModelType.SMOLDOCLING,
|
||||
ocr: Annotated[
|
||||
bool,
|
||||
typer.Option(
|
||||
@ -420,6 +436,9 @@ def convert(
|
||||
ocr_options.lang = ocr_lang_list
|
||||
|
||||
accelerator_options = AcceleratorOptions(num_threads=num_threads, device=device)
|
||||
pipeline_options: PaginatedPipelineOptions
|
||||
|
||||
if pipeline == PdfPipeline.STANDARD:
|
||||
pipeline_options = PdfPipelineOptions(
|
||||
allow_external_plugins=allow_external_plugins,
|
||||
enable_remote_services=enable_remote_services,
|
||||
@ -445,9 +464,6 @@ def convert(
|
||||
)
|
||||
pipeline_options.images_scale = 2
|
||||
|
||||
if artifacts_path is not None:
|
||||
pipeline_options.artifacts_path = artifacts_path
|
||||
|
||||
backend: Type[PdfDocumentBackend]
|
||||
if pdf_backend == PdfBackend.DLPARSE_V1:
|
||||
backend = DoclingParseDocumentBackend
|
||||
@ -464,6 +480,33 @@ def convert(
|
||||
pipeline_options=pipeline_options,
|
||||
backend=backend, # pdf_backend
|
||||
)
|
||||
elif pipeline == PdfPipeline.VLM:
|
||||
pipeline_options = VlmPipelineOptions()
|
||||
|
||||
if vlm_model == VlmModelType.GRANITE_VISION:
|
||||
pipeline_options.vlm_options = granite_vision_vlm_conversion_options
|
||||
elif vlm_model == VlmModelType.SMOLDOCLING:
|
||||
pipeline_options.vlm_options = smoldocling_vlm_conversion_options
|
||||
if sys.platform == "darwin":
|
||||
try:
|
||||
import mlx_vlm
|
||||
|
||||
pipeline_options.vlm_options = (
|
||||
smoldocling_vlm_mlx_conversion_options
|
||||
)
|
||||
except ImportError:
|
||||
_log.warning(
|
||||
"To run SmolDocling faster, please install mlx-vlm:\n"
|
||||
"pip install mlx-vlm"
|
||||
)
|
||||
|
||||
pdf_format_option = PdfFormatOption(
|
||||
pipeline_cls=VlmPipeline, pipeline_options=pipeline_options
|
||||
)
|
||||
|
||||
if artifacts_path is not None:
|
||||
pipeline_options.artifacts_path = artifacts_path
|
||||
|
||||
format_options: Dict[InputFormat, FormatOption] = {
|
||||
InputFormat.PDF: pdf_format_option,
|
||||
InputFormat.IMAGE: pdf_format_option,
|
||||
|
||||
@ -263,6 +263,11 @@ class ResponseFormat(str, Enum):
|
||||
MARKDOWN = "markdown"
|
||||
|
||||
|
||||
class InferenceFramework(str, Enum):
|
||||
MLX = "mlx"
|
||||
TRANSFORMERS = "transformers"
|
||||
|
||||
|
||||
class HuggingFaceVlmOptions(BaseVlmOptions):
|
||||
kind: Literal["hf_model_options"] = "hf_model_options"
|
||||
|
||||
@ -271,6 +276,7 @@ class HuggingFaceVlmOptions(BaseVlmOptions):
|
||||
llm_int8_threshold: float = 6.0
|
||||
quantized: bool = False
|
||||
|
||||
inference_framework: InferenceFramework
|
||||
response_format: ResponseFormat
|
||||
|
||||
@property
|
||||
@ -278,10 +284,19 @@ class HuggingFaceVlmOptions(BaseVlmOptions):
|
||||
return self.repo_id.replace("/", "--")
|
||||
|
||||
|
||||
smoldocling_vlm_mlx_conversion_options = HuggingFaceVlmOptions(
|
||||
repo_id="ds4sd/SmolDocling-256M-preview-mlx-bf16",
|
||||
prompt="Convert this page to docling.",
|
||||
response_format=ResponseFormat.DOCTAGS,
|
||||
inference_framework=InferenceFramework.MLX,
|
||||
)
|
||||
|
||||
|
||||
smoldocling_vlm_conversion_options = HuggingFaceVlmOptions(
|
||||
repo_id="ds4sd/SmolDocling-256M-preview",
|
||||
prompt="Convert this page to docling.",
|
||||
response_format=ResponseFormat.DOCTAGS,
|
||||
inference_framework=InferenceFramework.TRANSFORMERS,
|
||||
)
|
||||
|
||||
granite_vision_vlm_conversion_options = HuggingFaceVlmOptions(
|
||||
@ -289,9 +304,15 @@ granite_vision_vlm_conversion_options = HuggingFaceVlmOptions(
|
||||
# prompt="OCR the full page to markdown.",
|
||||
prompt="OCR this image.",
|
||||
response_format=ResponseFormat.MARKDOWN,
|
||||
inference_framework=InferenceFramework.TRANSFORMERS,
|
||||
)
|
||||
|
||||
|
||||
class VlmModelType(str, Enum):
|
||||
SMOLDOCLING = "smoldocling"
|
||||
GRANITE_VISION = "granite_vision"
|
||||
|
||||
|
||||
# Define an enum for the backend options
|
||||
class PdfBackend(str, Enum):
|
||||
"""Enum of valid PDF backends."""
|
||||
@ -327,13 +348,14 @@ class PipelineOptions(BaseModel):
|
||||
|
||||
|
||||
class PaginatedPipelineOptions(PipelineOptions):
|
||||
artifacts_path: Optional[Union[Path, str]] = None
|
||||
|
||||
images_scale: float = 1.0
|
||||
generate_page_images: bool = False
|
||||
generate_picture_images: bool = False
|
||||
|
||||
|
||||
class VlmPipelineOptions(PaginatedPipelineOptions):
|
||||
artifacts_path: Optional[Union[Path, str]] = None
|
||||
|
||||
generate_page_images: bool = True
|
||||
force_backend_text: bool = (
|
||||
@ -346,7 +368,6 @@ class VlmPipelineOptions(PaginatedPipelineOptions):
|
||||
class PdfPipelineOptions(PaginatedPipelineOptions):
|
||||
"""Options for the PDF pipeline."""
|
||||
|
||||
artifacts_path: Optional[Union[Path, str]] = None
|
||||
do_table_structure: bool = True # True: perform table structure extraction
|
||||
do_ocr: bool = True # True: perform OCR, replace programmatic PDF text
|
||||
do_code_enrichment: bool = False # True: perform code OCR
|
||||
@ -377,3 +398,8 @@ class PdfPipelineOptions(PaginatedPipelineOptions):
|
||||
)
|
||||
|
||||
generate_parsed_pages: bool = False
|
||||
|
||||
|
||||
class PdfPipeline(str, Enum):
|
||||
STANDARD = "standard"
|
||||
VLM = "vlm"
|
||||
|
||||
137
docling/models/hf_mlx_model.py
Normal file
137
docling/models/hf_mlx_model.py
Normal file
@ -0,0 +1,137 @@
|
||||
import logging
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Iterable, List, Optional
|
||||
|
||||
from docling.datamodel.base_models import Page, VlmPrediction
|
||||
from docling.datamodel.document import ConversionResult
|
||||
from docling.datamodel.pipeline_options import (
|
||||
AcceleratorDevice,
|
||||
AcceleratorOptions,
|
||||
HuggingFaceVlmOptions,
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.models.base_model import BasePageModel
|
||||
from docling.utils.accelerator_utils import decide_device
|
||||
from docling.utils.profiling import TimeRecorder
|
||||
|
||||
_log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HuggingFaceMlxModel(BasePageModel):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
enabled: bool,
|
||||
artifacts_path: Optional[Path],
|
||||
accelerator_options: AcceleratorOptions,
|
||||
vlm_options: HuggingFaceVlmOptions,
|
||||
):
|
||||
self.enabled = enabled
|
||||
|
||||
self.vlm_options = vlm_options
|
||||
|
||||
if self.enabled:
|
||||
|
||||
try:
|
||||
from mlx_vlm import generate, load # type: ignore
|
||||
from mlx_vlm.prompt_utils import apply_chat_template # type: ignore
|
||||
from mlx_vlm.utils import load_config, stream_generate # type: ignore
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"mlx-vlm is not installed. Please install it via `pip install mlx-vlm` to use MLX VLM models."
|
||||
)
|
||||
|
||||
repo_cache_folder = vlm_options.repo_id.replace("/", "--")
|
||||
self.apply_chat_template = apply_chat_template
|
||||
self.stream_generate = stream_generate
|
||||
|
||||
# PARAMETERS:
|
||||
if artifacts_path is None:
|
||||
artifacts_path = self.download_models(self.vlm_options.repo_id)
|
||||
elif (artifacts_path / repo_cache_folder).exists():
|
||||
artifacts_path = artifacts_path / repo_cache_folder
|
||||
|
||||
self.param_question = vlm_options.prompt # "Perform Layout Analysis."
|
||||
|
||||
## Load the model
|
||||
self.vlm_model, self.processor = load(artifacts_path)
|
||||
self.config = load_config(artifacts_path)
|
||||
|
||||
@staticmethod
|
||||
def download_models(
|
||||
repo_id: str,
|
||||
local_dir: Optional[Path] = None,
|
||||
force: bool = False,
|
||||
progress: bool = False,
|
||||
) -> Path:
|
||||
from huggingface_hub import snapshot_download
|
||||
from huggingface_hub.utils import disable_progress_bars
|
||||
|
||||
if not progress:
|
||||
disable_progress_bars()
|
||||
download_path = snapshot_download(
|
||||
repo_id=repo_id,
|
||||
force_download=force,
|
||||
local_dir=local_dir,
|
||||
# revision="v0.0.1",
|
||||
)
|
||||
|
||||
return Path(download_path)
|
||||
|
||||
def __call__(
|
||||
self, conv_res: ConversionResult, page_batch: Iterable[Page]
|
||||
) -> Iterable[Page]:
|
||||
for page in page_batch:
|
||||
assert page._backend is not None
|
||||
if not page._backend.is_valid():
|
||||
yield page
|
||||
else:
|
||||
with TimeRecorder(conv_res, "vlm"):
|
||||
assert page.size is not None
|
||||
|
||||
hi_res_image = page.get_image(scale=2.0) # 144dpi
|
||||
# hi_res_image = page.get_image(scale=1.0) # 72dpi
|
||||
|
||||
if hi_res_image is not None:
|
||||
im_width, im_height = hi_res_image.size
|
||||
|
||||
# populate page_tags with predicted doc tags
|
||||
page_tags = ""
|
||||
|
||||
if hi_res_image:
|
||||
if hi_res_image.mode != "RGB":
|
||||
hi_res_image = hi_res_image.convert("RGB")
|
||||
|
||||
prompt = self.apply_chat_template(
|
||||
self.processor, self.config, self.param_question, num_images=1
|
||||
)
|
||||
|
||||
start_time = time.time()
|
||||
# Call model to generate:
|
||||
output = ""
|
||||
for token in self.stream_generate(
|
||||
self.vlm_model,
|
||||
self.processor,
|
||||
prompt,
|
||||
[hi_res_image],
|
||||
max_tokens=4096,
|
||||
verbose=False,
|
||||
):
|
||||
output += token.text
|
||||
if "</doctag>" in token.text:
|
||||
break
|
||||
|
||||
generation_time = time.time() - start_time
|
||||
page_tags = output
|
||||
|
||||
# inference_time = time.time() - start_time
|
||||
# tokens_per_second = num_tokens / generation_time
|
||||
# print("")
|
||||
# print(f"Page Inference Time: {inference_time:.2f} seconds")
|
||||
# print(f"Total tokens on page: {num_tokens:.2f}")
|
||||
# print(f"Tokens/sec: {tokens_per_second:.2f}")
|
||||
# print("")
|
||||
page.predictions.vlm_response = VlmPrediction(text=page_tags)
|
||||
|
||||
yield page
|
||||
@ -14,8 +14,13 @@ from docling.backend.md_backend import MarkdownDocumentBackend
|
||||
from docling.backend.pdf_backend import PdfDocumentBackend
|
||||
from docling.datamodel.base_models import InputFormat, Page
|
||||
from docling.datamodel.document import ConversionResult, InputDocument
|
||||
from docling.datamodel.pipeline_options import ResponseFormat, VlmPipelineOptions
|
||||
from docling.datamodel.pipeline_options import (
|
||||
InferenceFramework,
|
||||
ResponseFormat,
|
||||
VlmPipelineOptions,
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.models.hf_mlx_model import HuggingFaceMlxModel
|
||||
from docling.models.hf_vlm_model import HuggingFaceVlmModel
|
||||
from docling.pipeline.base_pipeline import PaginatedPipeline
|
||||
from docling.utils.profiling import ProfilingScope, TimeRecorder
|
||||
@ -29,12 +34,6 @@ class VlmPipeline(PaginatedPipeline):
|
||||
super().__init__(pipeline_options)
|
||||
self.keep_backend = True
|
||||
|
||||
warnings.warn(
|
||||
"The VlmPipeline is currently experimental and may change in upcoming versions without notice.",
|
||||
category=UserWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
self.pipeline_options: VlmPipelineOptions
|
||||
|
||||
artifacts_path: Optional[Path] = None
|
||||
@ -58,6 +57,19 @@ class VlmPipeline(PaginatedPipeline):
|
||||
|
||||
self.keep_images = self.pipeline_options.generate_page_images
|
||||
|
||||
if (
|
||||
self.pipeline_options.vlm_options.inference_framework
|
||||
== InferenceFramework.MLX
|
||||
):
|
||||
self.build_pipe = [
|
||||
HuggingFaceMlxModel(
|
||||
enabled=True, # must be always enabled for this pipeline to make sense.
|
||||
artifacts_path=artifacts_path,
|
||||
accelerator_options=pipeline_options.accelerator_options,
|
||||
vlm_options=self.pipeline_options.vlm_options,
|
||||
),
|
||||
]
|
||||
else:
|
||||
self.build_pipe = [
|
||||
HuggingFaceVlmModel(
|
||||
enabled=True, # must be always enabled for this pipeline to make sense.
|
||||
@ -79,7 +91,9 @@ class VlmPipeline(PaginatedPipeline):
|
||||
|
||||
return page
|
||||
|
||||
def extract_text_from_backend(self, page: Page, bbox: BoundingBox | None) -> str:
|
||||
def extract_text_from_backend(
|
||||
self, page: Page, bbox: Union[BoundingBox, None]
|
||||
) -> str:
|
||||
# Convert bounding box normalized to 0-100 into page coordinates for cropping
|
||||
text = ""
|
||||
if bbox:
|
||||
|
||||
@ -10,13 +10,15 @@ from docling.datamodel.pipeline_options import (
|
||||
VlmPipelineOptions,
|
||||
granite_vision_vlm_conversion_options,
|
||||
smoldocling_vlm_conversion_options,
|
||||
smoldocling_vlm_mlx_conversion_options,
|
||||
)
|
||||
from docling.datamodel.settings import settings
|
||||
from docling.document_converter import DocumentConverter, PdfFormatOption
|
||||
from docling.pipeline.vlm_pipeline import VlmPipeline
|
||||
|
||||
sources = [
|
||||
"tests/data/2305.03393v1-pg9-img.png",
|
||||
# "tests/data/2305.03393v1-pg9-img.png",
|
||||
"tests/data/pdf/2305.03393v1-pg9.pdf",
|
||||
]
|
||||
|
||||
## Use experimental VlmPipeline
|
||||
@ -29,7 +31,10 @@ pipeline_options.force_backend_text = False
|
||||
# pipeline_options.accelerator_options.cuda_use_flash_attention2 = True
|
||||
|
||||
## Pick a VLM model. We choose SmolDocling-256M by default
|
||||
pipeline_options.vlm_options = smoldocling_vlm_conversion_options
|
||||
# pipeline_options.vlm_options = smoldocling_vlm_conversion_options
|
||||
|
||||
## Pick a VLM model. Fast Apple Silicon friendly implementation for SmolDocling-256M via MLX
|
||||
pipeline_options.vlm_options = smoldocling_vlm_mlx_conversion_options
|
||||
|
||||
## Alternative VLM models:
|
||||
# pipeline_options.vlm_options = granite_vision_vlm_conversion_options
|
||||
@ -63,9 +68,6 @@ for source in sources:
|
||||
|
||||
res = converter.convert(source)
|
||||
|
||||
print("------------------------------------------------")
|
||||
print("MD:")
|
||||
print("------------------------------------------------")
|
||||
print("")
|
||||
print(res.document.export_to_markdown())
|
||||
|
||||
@ -83,8 +85,17 @@ for source in sources:
|
||||
with (out_path / f"{res.input.file.stem}.json").open("w") as fp:
|
||||
fp.write(json.dumps(res.document.export_to_dict()))
|
||||
|
||||
pg_num = res.document.num_pages()
|
||||
res.document.save_as_json(
|
||||
out_path / f"{res.input.file.stem}.md",
|
||||
image_mode=ImageRefMode.PLACEHOLDER,
|
||||
)
|
||||
|
||||
res.document.save_as_markdown(
|
||||
out_path / f"{res.input.file.stem}.md",
|
||||
image_mode=ImageRefMode.PLACEHOLDER,
|
||||
)
|
||||
|
||||
pg_num = res.document.num_pages()
|
||||
print("")
|
||||
inference_time = time.time() - start_time
|
||||
print(
|
||||
|
||||
@ -26,7 +26,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
|
||||
* 🔒 Local execution capabilities for sensitive data and air-gapped environments
|
||||
* 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
|
||||
* 🔍 Extensive OCR support for scanned PDFs and images
|
||||
* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
|
||||
* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕🔥
|
||||
* 💻 Simple and convenient CLI
|
||||
|
||||
### Coming soon
|
||||
|
||||
@ -17,10 +17,15 @@ print(result.document.export_to_markdown()) # output: "### Docling Technical Re
|
||||
|
||||
You can also use Docling directly from your command line to convert individual files —be it local or by URL— or whole directories.
|
||||
|
||||
A simple example would look like this:
|
||||
```console
|
||||
docling https://arxiv.org/pdf/2206.01062
|
||||
```
|
||||
You can also use 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI:
|
||||
```bash
|
||||
docling --pipeline vlm --vlm-model smoldocling https://arxiv.org/pdf/2206.01062
|
||||
```
|
||||
This will use MLX acceleration on supported Apple Silicon hardware.
|
||||
|
||||
|
||||
To see all available options (export formats etc.) run `docling --help`. More details in the [CLI reference page](../reference/cli.md).
|
||||
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "docling"
|
||||
version = "2.27.0" # DO NOT EDIT, updated automatically
|
||||
version = "2.28.0" # DO NOT EDIT, updated automatically
|
||||
description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
|
||||
authors = [
|
||||
"Christoph Auer <cau@zurich.ibm.com>",
|
||||
@ -192,6 +192,7 @@ module = [
|
||||
"docling_ibm_models.*",
|
||||
"easyocr.*",
|
||||
"ocrmac.*",
|
||||
"mlx_vlm.*",
|
||||
"lxml.*",
|
||||
"huggingface_hub.*",
|
||||
"transformers.*",
|
||||
|
||||
@ -4,7 +4,7 @@
|
||||
"name": "powerpoint_sample",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.ms-powerpoint",
|
||||
"binary_hash": 1640759611026400292,
|
||||
"binary_hash": 15572290240354948364,
|
||||
"filename": "powerpoint_sample.pptx"
|
||||
},
|
||||
"furniture": {
|
||||
@ -75,6 +75,9 @@
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/7"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -94,19 +97,22 @@
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/15"
|
||||
"$ref": "#/texts/16"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/18"
|
||||
"$ref": "#/texts/19"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/26"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -119,14 +125,14 @@
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/9"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/10"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/11"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -139,9 +145,6 @@
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/11"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/12"
|
||||
},
|
||||
@ -150,6 +153,9 @@
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/14"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/15"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -163,10 +169,10 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/16"
|
||||
"$ref": "#/texts/17"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/17"
|
||||
"$ref": "#/texts/18"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -179,14 +185,14 @@
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/19"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/20"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/21"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/22"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -199,14 +205,14 @@
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/22"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/23"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/24"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/25"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -433,6 +439,33 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/8",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"label": "text",
|
||||
"prov": [
|
||||
{
|
||||
"page_no": 2,
|
||||
"bbox": {
|
||||
"l": 0.0,
|
||||
"t": 0.0,
|
||||
"r": 0.0,
|
||||
"b": 0.0,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
0,
|
||||
31
|
||||
]
|
||||
}
|
||||
],
|
||||
"orig": "Some notes on the second slide.",
|
||||
"text": "Some notes on the second slide."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
@ -461,7 +494,7 @@
|
||||
"marker": "1."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"self_ref": "#/texts/10",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
@ -490,7 +523,7 @@
|
||||
"marker": "2."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/10",
|
||||
"self_ref": "#/texts/11",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
@ -519,7 +552,7 @@
|
||||
"marker": "3."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/11",
|
||||
"self_ref": "#/texts/12",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
@ -548,7 +581,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/12",
|
||||
"self_ref": "#/texts/13",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
@ -577,7 +610,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/13",
|
||||
"self_ref": "#/texts/14",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
@ -606,7 +639,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/14",
|
||||
"self_ref": "#/texts/15",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
@ -635,7 +668,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/15",
|
||||
"self_ref": "#/texts/16",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
@ -662,7 +695,7 @@
|
||||
"text": "Some info:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/16",
|
||||
"self_ref": "#/texts/17",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
@ -691,7 +724,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/17",
|
||||
"self_ref": "#/texts/18",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
@ -720,7 +753,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/18",
|
||||
"self_ref": "#/texts/19",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
@ -747,7 +780,7 @@
|
||||
"text": "Maybe a list?"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/19",
|
||||
"self_ref": "#/texts/20",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
@ -776,7 +809,7 @@
|
||||
"marker": "1."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/20",
|
||||
"self_ref": "#/texts/21",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
@ -805,7 +838,7 @@
|
||||
"marker": "2."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/21",
|
||||
"self_ref": "#/texts/22",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
@ -834,7 +867,7 @@
|
||||
"marker": "3."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/22",
|
||||
"self_ref": "#/texts/23",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -863,7 +896,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/23",
|
||||
"self_ref": "#/texts/24",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -892,7 +925,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/24",
|
||||
"self_ref": "#/texts/25",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -919,6 +952,33 @@
|
||||
"text": "l3",
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/26",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"label": "text",
|
||||
"prov": [
|
||||
{
|
||||
"page_no": 3,
|
||||
"bbox": {
|
||||
"l": 0.0,
|
||||
"t": 0.0,
|
||||
"r": 0.0,
|
||||
"b": 0.0,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
0,
|
||||
53
|
||||
]
|
||||
}
|
||||
],
|
||||
"orig": "Final notes on the third slide.\nSecond line of notes.",
|
||||
"text": "Final notes on the third slide.\nSecond line of notes."
|
||||
}
|
||||
],
|
||||
"pictures": [],
|
||||
|
||||
Binary file not shown.
Loading…
Reference in New Issue
Block a user