mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Describe examples (#2262)

Browse Source 
* Update .py examples with clearer guidance,
update out of date imports and calls

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* Fix minimal.py string error, fix ruff format error

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

* fix more CI issues

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>

---------

Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>
This commit is contained in:
Mingxuan Zhao
2025-09-16 10:00:38 -04:00
committed by GitHub
parent 0e95171dd6
commit ff351fd40c
21 changed files with 608 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docs/examples/minimal_vlm_pipeline.py vendored
View File

@@ -1,3 +1,25 @@
# %% [markdown]
# Minimal VLM pipeline example: convert a PDF using a vision-language model.
#
# What this example does
# - Runs the VLM-powered pipeline on a PDF (by URL) and prints Markdown output.
# - Shows two setups: default (Transformers/SmolDocling) and macOS MPS/MLX.
#
# Prerequisites
# - Install Docling with VLM extras and the appropriate backend (Transformers or MLX).
# - Ensure your environment can download model weights (e.g., from Hugging Face).
#
# How to run
# - From the repository root, run: `python docs/examples/minimal_vlm_pipeline.py`.
# - The script prints the converted Markdown to stdout.
#
# Notes
# - `source` may be a local path or a URL to a PDF.
# - The second section demonstrates macOS MPS acceleration via MLX (`vlm_model_specs.SMOLDOCLING_MLX`).
# - For more configurations and model comparisons, see `docs/examples/compare_vlm_models.py`.
# %%
from docling.datamodel import vlm_model_specs
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
@@ -6,6 +28,7 @@ from docling.datamodel.pipeline_options import (
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline
# Convert a public arXiv PDF; replace with a local path if preferred.
source = "https://arxiv.org/pdf/2501.17887"
###### USING SIMPLE DEFAULT VALUES
@@ -26,7 +49,8 @@ print(doc.export_to_markdown())
###### USING MACOS MPS ACCELERATOR
# For more options see the compare_vlm_models.py example.
# Demonstrates using MLX on macOS with MPS acceleration (macOS only).
# For more options see the `compare_vlm_models.py` example.
pipeline_options = VlmPipelineOptions(
vlm_options=vlm_model_specs.SMOLDOCLING_MLX,