mirror of
https://github.com/DS4SD/docling.git
synced 2025-08-02 07:22:14 +00:00
53 lines
1.6 KiB
Python
53 lines
1.6 KiB
Python
import logging
|
|
from pathlib import Path
|
|
|
|
from docling_core.types.doc import PictureItem
|
|
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import PdfPipelineOptions, PicDescApiOptions
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
def main():
|
|
logging.basicConfig(level=logging.INFO)
|
|
|
|
input_doc_path = Path("./tests/data/2206.01062.pdf")
|
|
|
|
# This is using a local API server to do picture description.
|
|
# For example, you can launch it locally with:
|
|
# $ vllm serve "HuggingFaceTB/SmolVLM-256M-Instruct"
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.do_picture_description = True
|
|
pipeline_options.picture_description_options = PicDescApiOptions(
|
|
url="http://localhost:8000/v1/chat/completions",
|
|
params=dict(
|
|
model="HuggingFaceTB/SmolVLM-256M-Instruct",
|
|
seed=42,
|
|
max_completion_tokens=200,
|
|
),
|
|
prompt="Describe the image in three sentences. Be consise and accurate.",
|
|
timeout=90,
|
|
)
|
|
|
|
doc_converter = DocumentConverter(
|
|
format_options={
|
|
InputFormat.PDF: PdfFormatOption(
|
|
pipeline_options=pipeline_options,
|
|
)
|
|
}
|
|
)
|
|
result = doc_converter.convert(input_doc_path)
|
|
|
|
for element, _level in result.document.iterate_items():
|
|
if isinstance(element, PictureItem):
|
|
print(
|
|
f"Picture {element.self_ref}\n"
|
|
f"Caption: {element.caption_text(doc=result.document)}\n"
|
|
f"Annotations: {element.annotations}"
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|