mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
Add migration instructions to doc (cont)
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
parent
cd8e3dce76
commit
df3ff47914
82
docs/v2.md
82
docs/v2.md
@ -27,11 +27,19 @@ from docling.document_converter import (
|
|||||||
)
|
)
|
||||||
from docling.pipeline.simple_pipeline import SimplePipeline
|
from docling.pipeline.simple_pipeline import SimplePipeline
|
||||||
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
|
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
|
||||||
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
||||||
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
||||||
|
|
||||||
## Default initialization still works as before:
|
## Default initialization still works as before:
|
||||||
# doc_converter = DocumentConverter()
|
# doc_converter = DocumentConverter()
|
||||||
|
|
||||||
|
|
||||||
|
# previous `PipelineOptions` is now `PdfPipelineOptions`
|
||||||
|
pipeline_options = PdfPipelineOptions()
|
||||||
|
pipeline_options.do_ocr = False
|
||||||
|
pipeline_options.do_table_structure = True
|
||||||
|
#...
|
||||||
|
|
||||||
## Custom options are now defined per format.
|
## Custom options are now defined per format.
|
||||||
doc_converter = (
|
doc_converter = (
|
||||||
DocumentConverter( # all of the below is optional, has internal defaults.
|
DocumentConverter( # all of the below is optional, has internal defaults.
|
||||||
@ -44,17 +52,22 @@ doc_converter = (
|
|||||||
], # whitelist formats, non-matching files are ignored.
|
], # whitelist formats, non-matching files are ignored.
|
||||||
format_options={
|
format_options={
|
||||||
InputFormat.PDF: PdfFormatOption(
|
InputFormat.PDF: PdfFormatOption(
|
||||||
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
|
pipeline_options=pipeline_options, # pipeline options go here.
|
||||||
|
backend=PyPdfiumDocumentBackend # optional: pick an alternative backend
|
||||||
),
|
),
|
||||||
InputFormat.DOCX: WordFormatOption(
|
InputFormat.DOCX: WordFormatOption(
|
||||||
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
|
pipeline_cls=SimplePipeline # default for office formats and HTML
|
||||||
),
|
),
|
||||||
},
|
},
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
```
|
```
|
||||||
|
|
||||||
Note: If you work only with defaults, all remains the same as in Docling v1.
|
**Note**: If you work only with defaults, all remains the same as in Docling v1.
|
||||||
|
|
||||||
|
More options are shown in the following example units:
|
||||||
|
- [run_with_formats.py](docs/examples/run_with_formats.py)
|
||||||
|
- [custom_convert.py](docs/examples/custom_convert.py)
|
||||||
|
|
||||||
### Converting documents
|
### Converting documents
|
||||||
|
|
||||||
@ -82,6 +95,7 @@ input_files = [
|
|||||||
"tests/data/2206.01062.pdf",
|
"tests/data/2206.01062.pdf",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
# Directly pass list of files or streams to `convert_all`
|
||||||
conv_results_iter = doc_converter.convert_all(input_files) # previously `convert_batch`
|
conv_results_iter = doc_converter.convert_all(input_files) # previously `convert_batch`
|
||||||
|
|
||||||
```
|
```
|
||||||
@ -95,13 +109,67 @@ conv_results_iter = doc_converter.convert_all(input_files, raises_on_error=False
|
|||||||
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### Exporting documents into JSON, Markdown, Doctags
|
### Access document structures
|
||||||
|
|
||||||
We have simplified how you can access and export the converted document data, too.
|
We have simplified how you can access and export the converted document data, too. Our universal document representation
|
||||||
|
is now available in conversion results as a `DoclingDocument` object.
|
||||||
|
`DoclingDocument` provides a neat set of APIs to construct, iterate and export content in the document, as shown below.
|
||||||
|
|
||||||
TBD.
|
```python
|
||||||
|
conv_result = doc_converter.convert("https://arxiv.org/pdf/2408.09869") # previously `convert_single`
|
||||||
|
|
||||||
|
## Inspect the converted document:
|
||||||
|
conv_result.document.print_element_tree()
|
||||||
|
|
||||||
|
## Iterate the elements in reading order, including hierachy level:
|
||||||
|
for item, level in conv_result.document.iterate_items:
|
||||||
|
if isinstance(item, TextItem):
|
||||||
|
print(item.text)
|
||||||
|
elif isinstance(item, TableItem):
|
||||||
|
table_df: pd.DataFrame = item.export_to_dataframe()
|
||||||
|
print(table_df.to_markdown())
|
||||||
|
elif ...:
|
||||||
|
#...
|
||||||
|
```
|
||||||
|
|
||||||
|
## Export into JSON, Markdown, Doctags
|
||||||
|
**Note**: All `render_...` methods in `ConversionResult` have been removed in Docling v2,
|
||||||
|
and are now available on `DoclingDocument` as:
|
||||||
|
- `DoclingDocument.export_to_dict`
|
||||||
|
- `DoclingDocument.export_to_markdown`
|
||||||
|
- `DoclingDocument.export_to_document_tokens`
|
||||||
|
|
||||||
|
```python
|
||||||
|
conv_result = doc_converter.convert("https://arxiv.org/pdf/2408.09869") # previously `convert_single`
|
||||||
|
|
||||||
|
## Export to desired format:
|
||||||
|
print(json.dumps(conv_res.document.export_to_dict()))
|
||||||
|
print(conv_res.document.export_to_markdown())
|
||||||
|
print(conv_res.document.export_to_document_tokens())
|
||||||
|
```
|
||||||
|
|
||||||
### CLI
|
### CLI
|
||||||
|
|
||||||
TBD.
|
We updated the command line syntax of Docling v2 to support many formats. Examples are seen below.
|
||||||
|
```shell
|
||||||
|
# Convert a single file to Markdown (default)
|
||||||
|
docling myfile.pdf
|
||||||
|
|
||||||
|
# Convert a single file to Markdown and JSON, without OCR
|
||||||
|
docling myfile.pdf --to json --to md --no-ocr
|
||||||
|
|
||||||
|
# Convert PDF files in input directory to Markdown (default)
|
||||||
|
docling ./input/dir --from pdf
|
||||||
|
|
||||||
|
# Convert PDF and Word files in input directory to Markdown and JSON
|
||||||
|
docling ./input/dir --from pdf --from docx --to md --to json --output ./scratch
|
||||||
|
|
||||||
|
# Convert all supported files in input directory to Markdown, but abort on first error
|
||||||
|
docling ./input/dir --output ./scratch --abort-on-error
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Notable changes from v1:
|
||||||
|
- The standalone switches for different export formats are removed, and replaced with `--from` and `--to` arguments, to define input and output formats respectively.
|
||||||
|
- The new `--abort-on-error` will abort any batch conversion as soon an error is encountered
|
||||||
|
- The `--backend` option for PDFs was removed
|
Loading…
Reference in New Issue
Block a user