docs: Describe examples (#2262)

* 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update out of date imports and calls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

View File

@@ -1,3 +1,32 @@
# %% [markdown]
# Run conversion across multiple input formats and customize handling per type.
#
# What this example does
# - Demonstrates converting a mixed list of files (PDF, DOCX, PPTX, HTML, images, etc.).
# - Shows how to restrict `allowed_formats` and override `format_options` per format.
# - Writes results (Markdown, JSON, YAML) to `scratch/`.
#
# Prerequisites
# - Install Docling and any format-specific dependencies (e.g., for DOCX/PPTX parsing).
# - Ensure you can import `docling` from your Python environment.
# - YAML export requires `PyYAML` (`pip install pyyaml`).
#
# How to run
# - From the repository root, run: `python docs/examples/run_with_formats.py`.
# - Outputs are written under `scratch/` next to where you run the script.
# - If `scratch/` does not exist, create it before running.
#
# Customizing inputs
# - Update `input_paths` to include or remove files on your machine.
# - Non-whitelisted formats are ignored (see `allowed_formats`).
#
# Notes
# - `allowed_formats`: explicit whitelist of formats that will be processed.
# - `format_options`: per-format pipeline/backend overrides. Everything is optional; defaults exist.
# - Exports: per input, writes `<stem>.md`, `<stem>.json`, and `<stem>.yaml` in `scratch/`.
# %%
import json
import logging
from pathlib import Path
@@ -34,39 +63,41 @@ def main():
## to customize use:
doc_converter = (
DocumentConverter( # all of the below is optional, has internal defaults.
allowed_formats=[
InputFormat.PDF,
InputFormat.IMAGE,
InputFormat.DOCX,
InputFormat.HTML,
InputFormat.PPTX,
InputFormat.ASCIIDOC,
InputFormat.CSV,
InputFormat.MD,
], # whitelist formats, non-matching files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
),
},
)
# Below we explicitly whitelist formats and override behavior for some of them.
# You can omit this block and use the defaults (see above) for a quick start.
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
allowed_formats=[
InputFormat.PDF,
InputFormat.IMAGE,
InputFormat.DOCX,
InputFormat.HTML,
InputFormat.PPTX,
InputFormat.ASCIIDOC,
InputFormat.CSV,
InputFormat.MD,
], # whitelist formats, non-matching files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimplePipeline # or set a backend, e.g., MsWordDocumentBackend
# If you change the backend, remember to import it, e.g.:
# from docling.backend.msword_backend import MsWordDocumentBackend
),
},
)
conv_results = doc_converter.convert_all(input_paths)
for res in conv_results:
out_path = Path("scratch")
out_path = Path("scratch") # ensure this directory exists before running
print(
f"Document {res.input.file.name} converted."
f"\nSaved markdown output to: {out_path!s}"
)
_log.debug(res.document._export_to_indented_text(max_text_len=16))
# Export Docling document format to markdowndoc:
# Export Docling document to Markdown:
with (out_path / f"{res.input.file.stem}.md").open("w") as fp:
fp.write(res.document.export_to_markdown())